© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3190
    Prev
    Next
    INDEX
    Explanations

    version: or version =

    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_39_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
     generaciones
    0.40
    ananti
    0.39
    Data
    0.36
    CYCLE
    0.36
    傀
    0.35
    妃
    0.35
    equivalence
    0.35
     mercy
    0.35
    stability
    0.35
    antian
    0.35
    POSITIVE LOGITS
     συ
    0.43
     "\(
    0.41
    瓯
    0.40
     전문가
    0.39
     Besch
    0.38
    ध्यात्म
    0.37
     speaker
    0.37
     Experts
    0.37
    ParseException
    0.37
     halter
    0.36
    Activations Density 0.006%

    No Known Activations