© 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. 194489
    Prev
    Next
    INDEX
    Explanations

    version constraints

    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
    ె
    0.33
    ือ
    0.31
    IFIED
    0.30
    𝐤
    0.29
     ваше
    0.29
     द्विवेदी
    0.29
    戽
    0.29
    ση
    0.28
     electrolyte
    0.28
    EW
    0.28
    POSITIVE LOGITS
    QUOTE
    0.33
    倾向
    0.33
     Teor
    0.32
     serii
    0.32
     Face
    0.31
     Os
    0.31
     Madame
    0.31
     Osc
    0.30
     Arap
    0.30
     Touch
    0.30
    Activations Density 0.000%

    No Known Activations