© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232254
    Prev
    Next
    INDEX
    Explanations

    macbook pro or air

    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_6_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
    c
    1.67
    u
    1.39
    in
    1.33
    ik
    1.30
    ia
    1.27
    k
    1.25
    im
    1.06
    ie
    1.05
    ip
    1.03
    t
    1.02
    POSITIVE LOGITS
    з
    0.89
    ด
    0.82
    ล็อก
    0.81
    נ
    0.75
     burlap
    0.74
    р
    0.71
    τή
    0.70
    γο
    0.70
    м
    0.70
     LinearLayout
    0.70
    Activations Density 0.000%

    No Known Activations