© 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. 154544
    Prev
    Next
    INDEX
    Explanations

    hab

    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
    illas
    0.40
    éticas
    0.39
    
    0.38
    teren
    0.37
    ikki
    0.36
    impin
    0.36
     Dont
    0.35
    igations
    0.35
    traction
    0.35
    sounding
    0.35
    POSITIVE LOGITS
    喏
    0.45
    ancouver
    0.42
     Scottsdale
    0.38
    ystate
    0.38
    Cleveland
    0.38
     Down
    0.38
     customize
    0.38
    azier
    0.38
    pyrrolo
    0.38
    ရော
    0.37
    Activations Density 0.000%

    No Known Activations