© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79492
    Prev
    Next
    INDEX
    Explanations

    structured text punctuation

    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_31_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
    Focused
    0.27
    悹
    0.26
    either
    0.25
    whole
    0.25
     foremost
    0.25
    accompl
    0.25
     मंथ
    0.25
    一方面
    0.25
    畨
    0.24
     সীম
    0.24
    POSITIVE LOGITS
     благодаря
    0.27
     pharmacological
    0.27
    vature
    0.26
     BECAUSE
    0.25
     ELECT
    0.25
     Soh
    0.25
     כת
    0.25
     float
    0.25
     dzięki
    0.24
     elective
    0.24
    Activations Density 0.013%

    No Known Activations