© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7519
    Prev
    Next
    INDEX
    Explanations

    code, including programming language keywords, variable names, and references to specific libraries/frameworks (protobuf, R, etc.)

    oai_token-act-pair · gemini-2.0-flash

    programming code context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    AxisAlignment
    -0.68
    ]")]
    -0.50
    iann
    -0.49
    ingu
    -0.48
    pexpr
    -0.47
    SizeF
    -0.47
     مشين
    -0.47
    Население
    -0.47
     popolari
    -0.46
    ieb
    -0.46
    POSITIVE LOGITS
     doInBackground
    0.63
    prefixer
    0.54
     beginnetje
    0.54
    uterte
    0.54
     fieldNum
    0.51
     mayor
    0.50
    Mayor
    0.50
    apunov
    0.49
     localObject
    0.48
     Rukh
    0.48
    Activations Density 2.337%

    No Known Activations