© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9612
    Prev
    Next
    INDEX
    Explanations

    parts of computer code, especially related to network protocols and data structures

    oai_token-act-pair · gemini-2.0-flash

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     utafitiHapana
    -0.82
    ніципа
    -0.67
    mybatisplus
    -0.64
    хьтан
    -0.61
    djangoproject
    -0.57
     Winaray
    -0.56
     esternos
    -0.55
     censiti
    -0.55
    InjectAttribute
    -0.55
    UrlResolution
    -0.54
    POSITIVE LOGITS
    CloseOperation
    0.55
    ParseTree
    0.52
    sprogramm
    0.51
    RenderAtEndOf
    0.47
    addGap
    0.44
     cake
    0.42
     PERIOD
    0.42
    nextToken
    0.41
     Champ
    0.41
     getIs
    0.41
    Activations Density 0.788%

    No Known Activations