© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 146205
    Prev
    Next
    INDEX
    Explanations

    silliness or teh phrase

    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_0_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
    ;
    1.66
    א
    1.63
    지
    1.63
    ation
    1.48
    ado
    1.46
    에
    1.35
    도
    1.31
    其他
    1.30
     downsides
    1.26
    بد
    1.25
    POSITIVE LOGITS
    в
    1.80
    ра
    1.62
    ре
    1.46
    ла
    1.38
    си
    1.31
    ви
    1.24
    نيا
    1.20
    он
    1.18
    след
    1.17
     relativi
    1.14
    Activations Density 0.000%

    No Known Activations