© 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. 36153
    Prev
    Next
    INDEX
    Explanations

    you request

    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
     ಇದನ್ನು
    0.36
    絲
    0.35
     alttext
    0.35
     \%$,
    0.34
     คลิก
    0.34
     homeomorphic
    0.34
    נדי
    0.33
     sheaf
    0.33
    違
    0.33
     interpol
    0.33
    POSITIVE LOGITS
     huh
    0.47
     eh
    0.42
     Flint
    0.41
    ですか
    0.40
    !.
    0.38
    Popen
    0.36
    ![
    0.36
    गर
    0.35
    ですね
    0.35
    ++.
    0.35
    Activations Density 0.174%

    No Known Activations