© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142114
    Prev
    Next
    INDEX
    Explanations

    gabe or gab

    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_0_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
    i
    2.06
    d
    2.05
    in
    1.88
    re
    1.80
    a
    1.80
    1
    1.72
    b
    1.67
    ar
    1.65
    ل
    1.65
    m
    1.63
    POSITIVE LOGITS
    К
    1.51
    いる
    1.27
    𝗛
    1.26
     powied
    1.23
    Ա
    1.23
    Հ
    1.22
    kita
    1.20
    ﺘ
    1.19
    তা
    1.17
    স
    1.16
    Activations Density 0.000%

    No Known Activations