© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206440
    Prev
    Next
    INDEX
    Explanations

    cutoff score or passing criteria

    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_20_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
     conosce
    0.41
    遲
    0.36
     Admissions
    0.36
     dequeue
    0.35
    लंघन
    0.34
    ële
    0.34
     patted
    0.34
    ueux
    0.33
     avete
    0.33
     classmates
    0.33
    POSITIVE LOGITS
    FLOW
    0.36
    分布
    0.33
     Sonntag
    0.32
    잉
    0.31
    응
    0.31
    SSON
    0.31
     `<
    0.31
    랜드
    0.31
     flow
    0.30
    shaded
    0.30
    Activations Density 0.001%

    No Known Activations