© 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. 108450
    Prev
    Next
    INDEX
    Explanations

    plmn mn kit

    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
    t
    1.39
    k
    1.23
    g
    1.04
    các
    1.03
     KRS
    0.98
    inama
    0.96
    ᚕ
    0.96
    다라고
    0.94
    é
    0.93
    لي
    0.93
    POSITIVE LOGITS
     the
    1.46
    5
    1.40
    ant
    1.38
    1
    1.35
     it
    1.29
    up
    1.27
    ने
    1.23
    4
    1.23
     at
    1.21
    6
    1.21
    Activations Density 0.000%

    No Known Activations