© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122277
    Prev
    Next
    INDEX
    Explanations

    regardless of what

    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_3_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
    lim
    0.71
    മില്ല
    0.64
    ур
    0.63
    ید
    0.61
    sides
    0.61
     जागा
    0.60
    <0x85>
    0.59
     हिस्से
    0.59
    िवी
    0.58
     высоту
    0.58
    POSITIVE LOGITS
    1
    0.88
    on
    0.83
    es
    0.83
    െ
    0.82
    ot
    0.79
    en
    0.79
    (),
    0.78
     for
    0.77
    ından
    0.77
     depolar
    0.76
    Activations Density 0.001%

    No Known Activations