© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211047
    Prev
    Next
    INDEX
    Explanations

    Player's Handbook (PHB) as a core concept

    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_5_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
     i
    1.40
    涜
    1.02
    输入
    0.98
    ılır
    0.98
     և
    0.97
    0.95
    がある
    0.92
    した
    0.91
    形势
    0.91
     and
    0.90
    POSITIVE LOGITS
    as
    1.46
    ح
    1.36
    ა
    1.36
    6
    1.25
    ur
    1.17
    ون
    1.10
    that
    1.10
    ل
    1.09
    THAT
    1.09
    ą
    1.09
    Activations Density 0.000%

    No Known Activations