© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243098
    Prev
    Next
    INDEX
    Explanations

    information records

    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_40_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
    constitution
    0.52
    Constitution
    0.50
     constitution
    0.46
     Constitution
    0.44
    ⿺
    0.44
    แพ
    0.40
    宪
    0.40
    ༥
    0.38
    叐
    0.38
     dissolution
    0.38
    POSITIVE LOGITS
     records
    0.53
    records
    0.47
     RECORDS
    0.45
     record
    0.45
    RECORD
    0.45
    レコード
    0.44
     Records
    0.43
    記録
    0.43
     Record
    0.43
    Records
    0.42
    Activations Density 0.000%

    No Known Activations