© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198786
    Prev
    Next
    INDEX
    Explanations

    crush, crushes, crushing

    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_15_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
     vanuit
    0.47
    前面的
    0.47
     eléctrica
    0.46
    𝗌
    0.46
    嵊
    0.46
     verkaufen
    0.45
     brachte
    0.45
    }-(
    0.45
     zákaz
    0.45
     venezol
    0.44
    POSITIVE LOGITS
    Glo
    0.60
    Blob
    0.55
    Glasses
    0.55
    Focus
    0.52
    Puzzle
    0.52
    Wheat
    0.52
    Patch
    0.51
    Wor
    0.51
    Potato
    0.51
    Problems
    0.50
    Activations Density 0.002%

    No Known Activations