© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 151001
    Prev
    Next
    INDEX
    Explanations

    full opening

    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_60_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
     عاما
    0.36
    dialect
    0.35
     -
    0.34
     utilizzati
    0.34
     государ
    0.33
    驅
    0.33
     држа
    0.33
     administrativas
    0.33
     -"
    0.32
    awatt
    0.32
    POSITIVE LOGITS
     full
    0.55
    Full
    0.54
     Full
    0.53
    **
    0.50
    !;
    0.46
    **,
    0.44
     opening
    0.43
    full
    0.43
    !
    0.43
    Opening
    0.43
    Activations Density 0.000%

    No Known Activations