© 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. 206769
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

    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
    solving
    0.33
    ahren
    0.32
    vpn
    0.32
    Mobs
    0.31
    面对
    0.30
     наших
    0.30
    ¬
    0.30
    solve
    0.29
     unsere
    0.29
    u
    0.29
    POSITIVE LOGITS
    には
    0.33
     firmly
    0.33
    変換
    0.30
     comprises
    0.30
     Согласно
    0.30
     Reporter
    0.30
     compris
    0.30
     basically
    0.29
    タイプの
    0.29
    納得
    0.29
    Activations Density 0.000%

    No Known Activations