© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7329
    Prev
    Next
    INDEX
    Explanations

    ratios or rates, specifically the word "per"

    oai_token-act-pair · gemini-2.0-flash

    large numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    IntoConstraints
    -0.59
    RectangleBorder
    -0.58
     بيها
    -0.58
     AssemblyVersion
    -0.54
    +:+
    -0.52
    цездатний
    -0.51
    scalatest
    -0.51
    THISDAY
    -0.50
    hoeddwyd
    -0.50
    enegro
    -0.48
    POSITIVE LOGITS
     thousands
    0.77
    Thousands
    0.70
    thousands
    0.70
     Thousands
    0.67
     millions
    0.65
     THOUS
    0.65
     Millions
    0.61
     duiz
    0.60
    millions
    0.59
     billions
    0.59
    Activations Density 1.832%

    No Known Activations