© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261055
    Prev
    Next
    INDEX
    Explanations

    ingted

    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_5_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
    IS
    1.07
    I
    1.02
    THERE
    1.02
    3
    0.96
    dien
    0.94
    digit
    0.92
    drž
    0.91
    Prix
    0.87
    d
    0.86
    Jy
    0.85
    POSITIVE LOGITS
    на
    1.40
    in
    1.32
    ле
    1.31
    то
    1.28
    に
    1.18
    il
    1.17
    ات
    1.16
    िंग
    1.16
    에
    1.15
    о
    1.12
    Activations Density 0.000%

    No Known Activations