© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32611
    Prev
    Next
    INDEX
    Explanations

    css style element injection

    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_40_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
    celona
    0.40
     interlocking
    0.38
    </bbox>
    0.37
    ഞ്ഞു
    0.37
    Kep
    0.37
    ാൻഡ്
    0.37
    Paf
    0.36
     ribbons
    0.36
     হারিয়ে
    0.36
     gluing
    0.36
    POSITIVE LOGITS
     सें
    0.39
     rebel
    0.37
    hospital
    0.37
    본
    0.36
    템
    0.36
    ൭
    0.36
    pite
    0.35
    柠檬
    0.35
     सुनी
    0.34
    醫院
    0.34
    Activations Density 0.000%

    No Known Activations