© 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. 123315
    Prev
    Next
    INDEX
    Explanations

    Assassin's Creed

    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
     for
    0.93
     was
    0.88
     TIME
    0.80
     as
    0.79
     asso
    0.79
    l
    0.77
    "
    0.74
     AS
    0.73
    Center
    0.73
     an
    0.71
    POSITIVE LOGITS
    다면
    0.84
    های
    0.76
    ชค
    0.72
    gunakan
    0.70
    ים
    0.70
    дә
    0.69
    ५
    0.68
    ・・・。
    0.67
    ната
    0.67
    しなければ
    0.67
    Activations Density 0.001%

    No Known Activations