© 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. 161996
    Prev
    Next
    INDEX
    Explanations

    enabling others

    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
     sati
    0.40
     placement
    0.40
     FIXED
    0.39
    荟
    0.38
     fixed
    0.38
     maxWidth
    0.38
     Yung
    0.38
     மணிய
    0.37
     plac
    0.37
     spotlight
    0.37
    POSITIVE LOGITS
     competir
    0.43
    積極的に
    0.42
    ruik
    0.41
    fonos
    0.41
     ஒருவர்
    0.40
    懺
    0.39
     übernimmt
    0.38
    对接
    0.38
    糠
    0.38
    performs
    0.38
    Activations Density 0.031%

    No Known Activations