© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 6759
    Prev
    Next
    INDEX
    Explanations

    not

    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_44_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
    vesti
    0.39
    8
    0.38
    ാം
    0.37
     cxb
    0.36
     órgano
    0.36
     evoke
    0.36
    omized
    0.35
     دستگاه
    0.35
    笥
    0.35
     desempen
    0.35
    POSITIVE LOGITS
    Science
    0.39
     aut
    0.39
    Beginning
    0.38
     Science
    0.38
     Raw
    0.36
    Encoding
    0.36
     ავ
    0.36
     Yam
    0.36
     JANUARY
    0.36
     Ground
    0.36
    Activations Density 0.001%

    No Known Activations