© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219457
    Prev
    Next
    INDEX
    Explanations

    interest

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
     LOCCTR
    0.38
     Morn
    0.38
     sour
    0.38
    浸
    0.37
     Fatima
    0.36
     Peer
    0.36
     Burns
    0.35
     Peanut
    0.35
     Simpl
    0.35
     Duchess
    0.35
    POSITIVE LOGITS
    ǽ
    0.43
    pulse
    0.40
    descripcion
    0.38
    acketing
    0.38
    tug
    0.38
    astal
    0.38
    RESPONSE
    0.38
     ৮ম
    0.37
     encarg
    0.37
     그렇게
    0.37
    Activations Density 0.001%

    No Known Activations