© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41758
    Prev
    Next
    INDEX
    Explanations

    Russian Federation or president

    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
     utterances
    0.73
     alphanumeric
    0.68
     eighties
    0.64
     berfungsi
    0.62
     heresy
    0.62
    ेंट्स
    0.61
    h
    0.60
     extension
    0.59
    पना
    0.59
     armada
    0.59
    POSITIVE LOGITS
    يل
    0.92
    كو
    0.84
    ко
    0.76
    كوم
    0.76
    كا
    0.75
    то
    0.74
    كه
    0.74
    ргани
    0.74
    2
    0.73
    ру
    0.73
    Activations Density 0.003%

    No Known Activations