© 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. 39477
    Prev
    Next
    INDEX
    Explanations

    toilet flushing tanks

    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
     leverage
    0.20
    이야
    0.20
    으니
    0.19
    ﾅ
    0.18
     headlight
    0.18
    Rose
    0.17
    Pain
    0.17
    راہ
    0.17
    Roh
    0.17
    лежа
    0.17
    POSITIVE LOGITS
     Really
    0.21
     }-\
    0.20
     Constitutional
    0.19
     Quantification
    0.19
     )}
    0.19
    áis
    0.18
     Habe
    0.18
     Babel
    0.18
     )}$
    0.18
     Controversy
    0.18
    Activations Density 0.001%

    No Known Activations