© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108013
    Prev
    Next
    INDEX
    Explanations

    couples, trouble, wholesome

    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
     are
    1.24
     is
    1.23
     a
    1.20
    script
    1.02
    }-
    1.02
    с
    0.98
    O
    0.97
     Лю
    0.97
    。"
    0.94
    C
    0.93
    POSITIVE LOGITS
    ur
    1.52
    ir
    1.41
    )
    1.35
    il
    1.30
    ى
    1.27
    it
    1.24
    er
    1.23
    in
    1.22
    м
    1.21
    ം
    1.21
    Activations Density 0.001%

    No Known Activations