© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90522
    Prev
    Next
    INDEX
    Explanations

    literal

    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_11_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
     Detroit
    0.53
    로
    0.51
     Shreveport
    0.50
    齁
    0.50
    bounding
    0.50
     diathermy
    0.49
     konfl
    0.48
    Detroit
    0.48
     도입
    0.47
    唥
    0.47
    POSITIVE LOGITS
    ме
    0.52
     đa
    0.50
    от
    0.50
     والتي
    0.50
    𝙡
    0.50
     অমিত
    0.49
     যেটি
    0.49
     $|
    0.48
     అది
    0.48
    ты
    0.47
    Activations Density 0.017%

    No Known Activations