© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14479
    Prev
    Next
    INDEX
    Explanations

    code related to resolving file paths and handling errors within a testing context

    oai_token-act-pair · gemini-2.0-flash

    res

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     res
    -0.94
    Res
    -0.83
    res
    -0.79
     Res
    -0.75
     RES
    -0.59
    RES
    -0.59
     response
    -0.51
    Response
    -0.51
     ress
    -0.50
     responds
    -0.48
    POSITIVE LOGITS
    IntoConstraints
    0.67
    encodeWith
    0.65
    ⓧ
    0.63
    )];
    0.61
    InitVars
    0.61
    
    0.58
     lccn
    0.57
    rašymas
    0.57
     StatefulWidget
    0.57
     Drapeau
    0.55
    Activations Density 5.359%

    No Known Activations