© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89179
    Prev
    Next
    INDEX
    Explanations

    shameful or shameless

    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_11_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
     of
    0.70
    م
    0.64
    rophes
    0.58
     authentication
    0.58
    នៃ
    0.55
     consomm
    0.54
     measurement
    0.52
     fraude
    0.52
    مكن
    0.52
     consumes
    0.52
    POSITIVE LOGITS
    .|__
    0.68
    綦
    0.66
     Gör
    0.63
     Establish
    0.63
    }[\
    0.62
     Speakers
    0.62
     Abbas
    0.62
     Organizational
    0.61
     Imagen
    0.61
     Organ
    0.61
    Activations Density 0.001%

    No Known Activations