© 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. 220218
    Prev
    Next
    INDEX
    Explanations

    has/have been

    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
     crise
    0.43
    ┎
    0.39
    žení
    0.38
     ইংরেজ
    0.37
     칼
    0.35
     ನೇ
    0.35
     живело
    0.35
    сць
    0.35
     영국
    0.35
    adamente
    0.35
    POSITIVE LOGITS
    folio
    0.41
    hir
    0.38
    presence
    0.36
    Presence
    0.36
    philosoph
    0.36
     repurposed
    0.35
     方
    0.35
     complication
    0.34
     extreme
    0.34
    Mash
    0.34
    Activations Density 0.003%

    No Known Activations