© 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. 9431
    Prev
    Next
    INDEX
    Explanations

    Devanagari script, other non-ascii characters and also quotation marks.

    oai_token-act-pair · gemini-2.0-flash

    non-Latin script words or phrases

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

    non-english, math, and code

    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
    ne
    -0.54
    nis
    -0.48
    rag
    -0.47
    ile
    -0.47
    itu
    -0.47
     nature
    -0.46
    FieldDescriptor
    -0.46
    zen
    -0.45
     afin
    -0.45
     peman
    -0.45
    POSITIVE LOGITS
     للمعارف
    0.68
     useNavigate
    0.67
     useHistory
    0.67
    Населення
    0.64
    EndContext
    0.62
     ་་
    0.60
    arrings
    0.59
    jooq
    0.59
    ymce
    0.57
    tispiece
    0.57
    Activations Density 1.022%

    No Known Activations