© 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. 33876
    Prev
    Next
    INDEX
    Explanations

    art by Artgerm

    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
    T
    0.76
    O
    0.73
    S
    0.71
    دی
    0.64
    ﻔ
    0.63
    フルーツ
    0.62
     त्याच
    0.61
    M
    0.59
    بی
    0.59
     علی
    0.59
    POSITIVE LOGITS
    t
    1.11
    ت
    0.89
    تون
    0.79
    l
    0.79
    -
    0.74
    تك
    0.73
    تن
    0.68
    r
    0.68
    '
    0.68
    d
    0.64
    Activations Density 0.006%

    No Known Activations