© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258952
    Prev
    Next
    INDEX
    Explanations

    deformation behavior

    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_22_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
    ˇ
    0.41
    ucian
    0.40
     வருட
    0.40
    ظر
    0.39
     pokud
    0.39
    )}/>
    0.39
     teore
    0.39
     alleine
    0.39
     cauza
    0.39
    erca
    0.38
    POSITIVE LOGITS
     Arabic
    0.42
     Design
    0.39
     Sails
    0.38
     스타일
    0.38
    🖊
    0.38
     लाभार्थियों
    0.38
     Electric
    0.37
     건설
    0.37
     qay
    0.37
     стиль
    0.36
    Activations Density 0.003%

    No Known Activations