© 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-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24281
    Prev
    Next
    INDEX
    Explanations

    bath

    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
    aj
    0.78
    au
    0.77
    র
    0.75
    é
    0.74
     Prabh
    0.70
    <unused2018>
    0.70
    el
    0.70
    óst
    0.69
    দর্শক
    0.68
    fZ
    0.68
    POSITIVE LOGITS
     retort
    0.65
    ה
    0.65
    я
    0.63
    /
    0.63
    ление
    0.61
    s
    0.59
    しばらく
    0.55
    над
    0.54
     righteousness
    0.54
     ваше
    0.54
    Activations Density 0.002%

    No Known Activations