© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45913
    Prev
    Next
    INDEX
    Explanations

    OPC UA

    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_13_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
    k
    0.64
    to
    0.64
    २
    0.63
    theta
    0.62
    V
    0.61
     easy
    0.59
     \
    0.57
     TO
    0.56
    R
    0.55
    F
    0.55
    POSITIVE LOGITS
    HasStarred
    0.53
    ньше
    0.48
     fissures
    0.46
     permeated
    0.45
     perched
    0.44
    하루
    0.44
    டியாக
    0.44
     continuamos
    0.43
    書店
    0.43
     preocupaciones
    0.43
    Activations Density 0.002%

    No Known Activations