© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54585
    Prev
    Next
    INDEX
    Explanations

    question answer pairs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     arras
    0.37
     considerando
    0.36
     απε
    0.36
     desider
    0.35
     (((
    0.35
     obten
    0.34
    !!!!!!!!!!!!!!!!
    0.34
    ّد
    0.34
    하였
    0.33
    뵈
    0.33
    POSITIVE LOGITS
    kWh
    0.46
    Haupt
    0.40
     '-
    0.38
    Coords
    0.38
     Venezuel
    0.38
    getCharAt
    0.38
    '=>'
    0.38
     litres
    0.37
    pageno
    0.37
     ryt
    0.36
    Activations Density 0.000%

    No Known Activations