© 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. 14092
    Prev
    Next
    INDEX
    Explanations

    C and C++ code

    oai_token-act-pair · gemini-2.0-flash

    terms related to size or elements

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

    code variable lengths

    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
    OGND
    -0.72
    LookAnd
    -0.69
     Meksiku
    -0.66
    MigrationBuilder
    -0.65
    клопе
    -0.65
    Дереккөздер
    -0.60
     beginnetje
    -0.59
     <<<<<<<<<<<<<<
    -0.58
    ніципалі
    -0.57
    Népesség
    -0.56
    POSITIVE LOGITS
     size
    0.66
     elements
    0.56
    خبار
    0.55
     Size
    0.54
     element
    0.53
     مشين
    0.52
    elements
    0.52
    zień
    0.52
     taille
    0.52
    cont
    0.51
    Activations Density 3.827%

    No Known Activations