© 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
    2. Gemma-3-27B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 222035
    Prev
    Next
    INDEX
    Explanations

    linked, distinct, forces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nueve
    0.36
    なくなった
    0.35
     девя
    0.34
    es
    0.34
    i
    0.34
    Off
    0.33
     derecha
    0.33
    And
    0.33
    ů
    0.33
    Options
    0.32
    POSITIVE LOGITS
    лися
    0.38
    다면
    0.36
    ли
    0.35
    owali
    0.35
    ap
    0.34
    !"));
    0.33
    yz
    0.33
     nagging
    0.32
    onz
    0.32
    أن
    0.31
    Activations Density 0.153%

    No Known Activations