© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11587
    Prev
    Next
    INDEX
    Explanations

    name before stage, image, deploy

    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_40_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
    portable
    0.38
    ituus
    0.36
    Nou
    0.35
    simile
    0.34
     obrig
    0.33
    姒
    0.33
     prototyping
    0.32
    Fancy
    0.32
     වලින්
    0.32
     विविध
    0.32
    POSITIVE LOGITS
    ंग्रेस
    0.33
     bottomLeft
    0.33
     bygg
    0.33
     construir
    0.33
    打电话
    0.33
    GetBytes
    0.32
     गले
    0.32
    棟
    0.32
    逗
    0.32
     Key
    0.31
    Activations Density 0.004%

    No Known Activations