© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198598
    Prev
    Next
    INDEX
    Explanations

    documented, structured, best practices

    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_27_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
    .*/
    0.34
     लता
    0.33
    ;\
    0.33
    ;.
    0.33
     nontrivial
    0.32
     п
    0.32
    。.
    0.32
    vou
    0.32
    чено
    0.31
    п
    0.31
    POSITIVE LOGITS
    たちが
    0.37
    ර්ග
    0.33
    様専用
    0.33
    パール
    0.33
    )?,
    0.32
     نباش
    0.31
     অধিকাংশই
    0.31
     لوگ
    0.31
    いましたが
    0.31
    ?),
    0.30
    Activations Density 0.001%

    No Known Activations