© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13928
    Prev
    Next
    INDEX
    Explanations

    sentences describing actions or events regarding a specific situation

    oai_token-act-pair · gemini-2.0-flash

    Abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     BON
    -0.69
     LEG
    -0.68
     CUR
    -0.68
     MASS
    -0.67
     PLAT
    -0.66
     PUR
    -0.66
     VAL
    -0.65
     BUL
    -0.65
     MAT
    -0.65
     RET
    -0.65
    POSITIVE LOGITS
    Fordítás
    0.43
    NHL
    0.37
    OSHA
    0.37
    NHS
    0.36
    GC
    0.36
    QCD
    0.36
    HC
    0.36
    screenshots
    0.35
    UI
    0.35
    US
    0.35
    Activations Density 42.641%

    No Known Activations