© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14594
    Prev
    Next
    INDEX
    Explanations

    proper nouns such as locations, organizations and people's names, often used in formal contexts

    oai_token-act-pair · gemini-2.0-flash

    proper nouns and terms related to broadcasting or telecommunications

    np_token-act-pair-logits · gpt-4o-mini

    Canadian location/organization names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.71
     Canada
    -0.66
     Canadá
    -0.64
     Cana
    -0.62
     ويكيميديا
    -0.62
     CANADA
    -0.60
     بيها
    -0.59
     Whistler
    -0.59
    ✭✭
    -0.58
     Canadian
    -0.58
    POSITIVE LOGITS
    المشاركات
    0.49
    wezig
    0.46
    Fine
    0.44
    таратура
    0.43
    grees
    0.42
    NegativeButton
    0.41
    couvrez
    0.41
     Exactos
    0.41
    windowFixed
    0.40
    izer
    0.40
    Activations Density 0.270%

    No Known Activations