© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232634
    Prev
    Next
    INDEX
    Explanations

    legal and public records

    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_32_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
     accepting
    0.35
    Ultimately
    0.35
    uil
    0.34
    矨
    0.34
    ானது
    0.33
     absoluta
    0.33
    йня
    0.33
    Reaction
    0.32
    amand
    0.32
     yard
    0.32
    POSITIVE LOGITS
     estánd
    0.41
    储存
    0.39
     ተጨማሪ
    0.37
    缮
    0.36
     Vis
    0.34
     vis
    0.34
    ZERO
    0.34
     viz
    0.33
    损坏
    0.33
     visor
    0.33
    Activations Density 0.000%

    No Known Activations