© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1712
    Prev
    Next
    INDEX
    Explanations

    code context / programming syntax

    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
    pppp
    0.39
     ম্যাচের
    0.37
    Particles
    0.37
    getJSONObject
    0.37
    __[
    0.37
    坦
    0.37
    sommets
    0.36
    wins
    0.36
    getName
    0.35
    ("|
    0.35
    POSITIVE LOGITS
     UIImage
    0.41
     UserDefaults
    0.40
    agement
    0.36
    UIImage
    0.35
     HStack
    0.35
     closure
    0.34
    closure
    0.33
     loss
    0.33
    CBUUID
    0.33
    駆
    0.33
    Activations Density 0.040%

    No Known Activations