© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44879
    Prev
    Next
    INDEX
    Explanations

    job offers and dimensions

    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_22_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
     QUE
    0.46
     masa
    0.44
    рят
    0.44
     consulta
    0.43
     Housewives
    0.42
     dukk
    0.41
    ワ
    0.41
    rocchia
    0.41
     சர்வதேச
    0.41
     Consulta
    0.41
    POSITIVE LOGITS
    แมนเชสเตอร์ซิตี
    0.51
    KPI
    0.47
    l
    0.45
     ακόμα
    0.44
    大家的
    0.43
    CD
    0.42
    listeners
    0.42
    戊
    0.41
     poveć
    0.41
    Storage
    0.41
    Activations Density 0.000%

    No Known Activations