© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12221
    Prev
    Next
    INDEX
    Explanations

    code and math formulas

    oai_token-act-pair · gemini-2.0-flash

    fr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    fr
    -1.08
     fr
    -1.05
    FR
    -0.95
     FR
    -0.94
     Fr
    -0.83
    Fr
    -0.80
    Fri
    -0.74
    fri
    -0.73
     Fri
    -0.71
     fri
    -0.68
    POSITIVE LOGITS
    abestanden
    0.79
    ThroughAttribute
    0.79
    styleType
    0.66
    Geplaatst
    0.64
    NameInMap
    0.60
    ########.
    0.57
    Hochspringen
    0.56
    NUMX
    0.55
    Rüyada
    0.55
     ProtoMessage
    0.54
    Activations Density 5.478%

    No Known Activations