© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129389
    Prev
    Next
    INDEX
    Explanations

    perhaps even

    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_6_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
    as
    0.99
    1
    0.95
    ס
    0.88
    On
    0.82
    Count
    0.81
    There
    0.80
    Re
    0.79
    ون
    0.79
    6
    0.77
    ام
    0.76
    POSITIVE LOGITS
     devoured
    0.73
     σε
    0.65
     refuted
    0.64
     scolded
    0.63
     transitioned
    0.62
     enveloped
    0.62
     assayed
    0.61
     accuses
    0.61
     misspelled
    0.61
     чувство
    0.60
    Activations Density 0.001%

    No Known Activations