© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194799
    Prev
    Next
    INDEX
    Explanations

    center of gravity

    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_27_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
     inten
    0.37
    Brows
    0.36
     LID
    0.36
     asc
    0.35
    tested
    0.35
    Thu
    0.35
    鶉
    0.35
    Adjacent
    0.35
    worthy
    0.35
     MIND
    0.34
    POSITIVE LOGITS
    过多
    0.42
    ကြာ
    0.39
    ución
    0.38
    اقة
    0.37
    瓦
    0.37
    ደጋ
    0.37
    将会
    0.36
     Información
    0.36
     necesaria
    0.36
    ustomer
    0.35
    Activations Density 0.003%

    No Known Activations