© 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. 9797
    Prev
    Next
    INDEX
    Explanations

    a constellation of terms frequently found together related to both medical topics and coding/programming/IT.

    oai_token-act-pair · gemini-2.0-flash

    conjunctions

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

    and in many languages

    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
    BeginContext
    -0.76
     oder
    -0.65
    __':
    -0.62
     eller
    -0.62
    UserScript
    -0.59
    __':
    -0.59
     ExecuteAsync
    -0.56
     oprot
    -0.55
    ImageContext
    -0.54
     protoimpl
    -0.53
    POSITIVE LOGITS
     and
    2.50
    และ
    1.20
     и
    1.10
     và
    1.07
    and
    1.01
    和
    0.92
    性和
    0.90
     și
    0.90
    および
    0.87
     και
    0.86
    Activations Density 22.386%

    No Known Activations