© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58448
    Prev
    Next
    INDEX
    Explanations

    comets

    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
    oe
    1.11
    d
    1.06
    ond
    1.02
    oo
    1.02
    ,
    1.01
    ul
    0.98
    IT
    0.98
    le
    0.97
    ohl
    0.95
    ı
    0.94
    POSITIVE LOGITS
    ین
    1.52
    ма
    1.36
    is
    1.21
    ти
    1.21
    ні
    1.08
    ان
    1.06
    "،
    1.05
    по
    1.03
     отношении
    1.03
    these
    1.02
    Activations Density 0.000%

    No Known Activations