© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139037
    Prev
    Next
    INDEX
    Explanations

    artillery, cavalry, tactics, spotting

    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_12_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
     conoc
    0.64
     división
    0.62
     conocida
    0.58
    芒
    0.57
     quatre
    0.56
     أن
    0.56
    وق
    0.56
    って
    0.55
     ל
    0.54
     artillery
    0.54
    POSITIVE LOGITS
    h
    0.71
    hala
    0.64
    halla
    0.59
    hz
    0.56
    hse
    0.55
    hood
    0.54
    jami
    0.52
    jah
    0.51
    je
    0.51
    omega
    0.51
    Activations Density 0.002%

    No Known Activations