© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10424
    Prev
    Next
    INDEX
    Explanations

    the letter "g", especially as it relates to its measurement using simple tools

    oai_token-act-pair · gemini-2.0-flash

    Physics and Mathematics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ]--;
    -1.02
     <=",
    -1.00
    AndEndTag
    -0.96
    ArrowToggle
    -0.95
    migrationBuilder
    -0.95
    findpost
    -0.90
     resourceCulture
    -0.84
    //
    -0.84
     ProtoMessage
    -0.84
     ویکی‌پدی
    -0.81
    POSITIVE LOGITS
    importe
    0.45
    rest
    0.44
     consider
    0.40
     straight
    0.39
     nhân
    0.39
    зий
    0.39
     direct
    0.38
     directly
    0.37
     Consider
    0.37
     piece
    0.37
    Activations Density 1.652%

    No Known Activations