© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110303
    Prev
    Next
    INDEX
    Explanations

    y followed by Eddy Current

    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
    Not in Any Lists

    No Comments

    Negative Logits
    った
    1.36
    ле
    1.29
    つ
    1.23
    ра
    1.18
    ため
    1.13
    ない
    1.10
    ى
    1.09
    다
    1.08
    лить
    1.05
    く
    1.02
    POSITIVE LOGITS
    h
    1.22
     it
    1.17
    n
    1.17
    '
    1.16
    p
    1.14
    ok
    1.11
     It
    1.05
    c
    1.05
     not
    1.04
    g
    1.03
    Activations Density 0.000%

    No Known Activations