© 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. 14587
    Prev
    Next
    INDEX
    Explanations

    various words in code or project-descriptions

    oai_token-act-pair · gemini-2.0-flash

    software projects

    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
    datable
    -0.55
    '))
    -0.54
     tslint
    -0.52
    namentales
    -0.52
    )");
    -0.52
     Wiktionnaire
    -0.51
    AndEndTag
    -0.51
    üyada
    -0.51
    providedIn
    -0.50
    lijkse
    -0.50
    POSITIVE LOGITS
    CloseOperation
    0.74
    iastes
    0.58
     CreateTagHelper
    0.55
     BioLib
    0.51
    ẾT
    0.46
    LabelTagHelper
    0.46
    ̀u
    0.46
    istoitu
    0.46
    ColumnInfo
    0.43
    aluno
    0.43
    Activations Density 1.359%

    No Known Activations