© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35648
    Prev
    Next
    INDEX
    Explanations

    cd followed by project name

    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_31_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
     ಹುಡು
    0.39
    trunc
    0.38
    Conc
    0.38
    @[+][
    0.36
    Indeed
    0.36
     अभिव्यक्ति
    0.36
    RETURNS
    0.36
    ನಿಯ
    0.36
    returning
    0.36
    IENTO
    0.36
    POSITIVE LOGITS
     Hank
    0.40
     Recycling
    0.39
     shook
    0.39
     mukaan
    0.38
     pH
    0.38
    汚
    0.38
     able
    0.37
     terecht
    0.36
     spring
    0.36
     Surplus
    0.36
    Activations Density 0.002%

    No Known Activations