© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59475
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ו
    1.63
    ه
    1.59
    ש
    1.52
    ח
    1.45
    я
    1.41
    ה
    1.35
    ا
    1.34
    ק
    1.33
    ী
    1.32
    ني
    1.30
    POSITIVE LOGITS
    to
    1.07
    have
    1.02
    p
    1.00
    AS
    0.98
    AD
    0.98
    pa
    0.98
    us
    0.95
    ts
    0.94
    US
    0.94
    OR
    0.93
    Activations Density 0.000%

    No Known Activations