© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12775
    Prev
    Next
    INDEX
    Explanations

    Java code structural and annotation terms

    oai_token-act-pair · gemini-2.0-flash

    code annotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Efq
    -0.90
    VolleyError
    -0.83
     Jefus
    -0.79
    ſelves
    -0.78
     Monfieur
    -0.76
     doubtnut
    -0.73
     Houſe
    -0.73
    TProtocol
    -0.69
    Tikang
    -0.68
     preſent
    -0.68
    POSITIVE LOGITS
     Đ
    0.47
     tích
    0.47
    مل
    0.47
     Pantry
    0.46
     regel
    0.45
    IZING
    0.45
     henvisninger
    0.45
    rande
    0.45
     виправивши
    0.44
    titanic
    0.44
    Activations Density 17.213%

    No Known Activations