© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58778
    Prev
    Next
    INDEX
    Explanations

    faintest

    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_11_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
     UID
    0.61
    vá
    0.53
    )}^{\
    0.52
    ak
    0.51
    mente
    0.51
     schützen
    0.50
    ör
    0.50
    aping
    0.50
    APPING
    0.50
    ain
    0.49
    POSITIVE LOGITS
    ン
    0.54
    க்த
    0.51
     disagree
    0.51
     fringe
    0.50
     associates
    0.48
     startups
    0.48
     firms
    0.46
    $
    0.46
     herds
    0.46
     slaughter
    0.46
    Activations Density 0.000%

    No Known Activations