© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104784
    Prev
    Next
    INDEX
    Explanations

    multilingual sequences

    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_1_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
    :
    1.23
    то
    1.17
    м
    1.16
    ции
    1.11
    в
    1.11
    ني
    1.09
    ()];
    1.09
    の話
    1.07
    ס
    1.05
    스가
    1.04
    POSITIVE LOGITS
    d
    1.53
    ll
    1.51
    line
    1.43
    l
    1.33
    can
    1.30
    د
    1.24
     in
    1.23
    lari
    1.23
    llo
    1.21
    lng
    1.20
    Activations Density 0.006%

    No Known Activations