© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5703
    Prev
    Next
    INDEX
    Explanations

    command redirection to `/dev/null`

    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_39_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
    匝
    0.41
    стойчи
    0.39
    ulmonary
    0.39
     Gry
    0.38
    வதற்கான
    0.37
     lingkungan
    0.37
    सौ
    0.37
     Сол
    0.36
    conserv
    0.36
    ोजक
    0.35
    POSITIVE LOGITS
    process
    0.41
     gamut
    0.40
     process
    0.40
    attachments
    0.38
     $>$
    0.37
    iesi
    0.37
    tera
    0.37
    ិច
    0.37
    >(
    0.36
    OfString
    0.36
    Activations Density 0.002%

    No Known Activations