© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45393
    Prev
    Next
    INDEX
    Explanations

    Philadelphia Story, Eagles, Fry, Dick, VI

    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_3_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
     contrôle
    0.66
    ан
    0.60
     comis
    0.60
    д
    0.59
     iako
    0.57
    ંદ્ર
    0.56
     revel
    0.56
     conm
    0.56
    ীদের
    0.55
    عي
    0.55
    POSITIVE LOGITS
    -
    0.76
    ts
    0.75
    tk
    0.74
    digit
    0.74
    lar
    0.72
    plans
    0.72
    +
    0.72
    dish
    0.71
    norms
    0.71
    larg
    0.71
    Activations Density 0.003%

    No Known Activations