© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106700
    Prev
    Next
    INDEX
    Explanations

    following instructions

    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_1_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
     on
    1.05
     inextricably
    0.95
     are
    0.92
     to
    0.87
     like
    0.86
    ş
    0.85
    on
    0.84
     around
    0.83
     at
    0.83
     feces
    0.81
    POSITIVE LOGITS
    i
    0.86
    га
    0.77
    mene
    0.77
    man
    0.76
    م
    0.76
    ively
    0.75
    nv
    0.74
    ia
    0.73
    matic
    0.70
    marine
    0.68
    Activations Density 0.001%

    No Known Activations