© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213156
    Prev
    Next
    INDEX
    Explanations

    book titles

    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_50_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
    뎃
    0.48
    RGB
    0.42
     pcMove
    0.41
    SEY
    0.41
     गार्डन
    0.40
     एमसी
    0.39
     imposed
    0.39
    돛
    0.38
    叄
    0.38
    ft
    0.37
    POSITIVE LOGITS
     लॉ
    0.42
    𝙘
    0.40
    Pacific
    0.40
     C
    0.39
    ToString
    0.38
    agara
    0.37
     Duc
    0.37
    efa
    0.36
     Dominicana
    0.35
    يانة
    0.35
    Activations Density 0.001%

    No Known Activations