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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11486
    Prev
    Next
    INDEX
    Explanations

    words of reference typically found in an academic context, such as locations, government, medical, and school

    oai_token-act-pair · gemini-2.0-flash

    institutions and organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     antiquities
    -0.43
     createState
    -0.40
     hacker
    -0.39
     NSCoder
    -0.38
     createSprite
    -0.37
     Hände
    -0.37
     naturalist
    -0.37
     butler
    -0.36
     rhinoceros
    -0.36
     kangaroo
    -0.35
    POSITIVE LOGITS
    ContentAsync
    0.71
     المعيارى
    0.69
    出版年
    0.66
    ISupport
    0.63
    featureID
    0.60
    >{"
    0.60
    IsContent
    0.60
    ματο
    0.59
    .-
    0.58
     Whose
    0.57
    Activations Density 33.581%

    No Known Activations