© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92097
    Prev
    Next
    INDEX
    Explanations

    Som

    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
    ŵ
    0.48
     ألمانيا
    0.45
    хів
    0.44
    ið
    0.44
    Connection
    0.44
    ukasz
    0.42
     చేసుకోవ
    0.42
    им
    0.41
    ító
    0.40
    ولندا
    0.40
    POSITIVE LOGITS
    y
    0.66
    ers
    0.61
    ERS
    0.49
    bre
    0.43
     Z
    0.41
     sober
    0.41
     nominations
    0.40
     returns
    0.39
     passport
    0.39
    者
    0.39
    Activations Density 0.000%

    No Known Activations