© 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. 205611
    Prev
    Next
    INDEX
    Explanations

    case management

    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
    st
    0.97
    ő
    0.97
    ens
    0.93
    ۳
    0.93
    ip
    0.92
    us
    0.91
    ates
    0.90
    id
    0.90
    let
    0.90
    ral
    0.89
    POSITIVE LOGITS
    ,
    1.14
     capi
    1.12
    การ
    1.08
     veinte
    1.04
     capilla
    1.00
     cambiando
    0.98
     março
    0.97
     patente
    0.97
     núi
    0.97
    ש
    0.97
    Activations Density 0.000%

    No Known Activations