© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 106905
    Prev
    Next
    INDEX
    Explanations

    besser blocks

    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_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    as
    1.50
    o
    1.45
    ك
    1.39
    e
    1.31
    1
    1.14
    و
    1.13
    et
    1.10
    on
    1.09
    ка
    1.05
    ে
    1.05
    POSITIVE LOGITS
    ين
    1.32
    dır
    1.19
    miş
    1.13
    nome
    1.11
    IR
    1.02
    IENT
    1.02
    ATIVE
    0.99
    nama
    0.96
    виси
    0.94
    ACON
    0.94
    Activations Density 0.000%

    No Known Activations