© 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. 52890
    Prev
    Next
    INDEX
    Explanations

    research studies

    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
    ysters
    0.39
    调查
    0.39
    samples
    0.38
    遅
    0.38
    ISTA
    0.38
    sample
    0.37
    喜
    0.37
    answers
    0.37
     seafood
    0.36
    sampled
    0.36
    POSITIVE LOGITS
    MatchType
    0.43
     Mikh
    0.39
    ocsát
    0.39
     sociedade
    0.38
     巻
    0.38
     কণ
    0.38
     episodios
    0.37
    Twe
    0.37
     Illustrated
    0.37
     Harsh
    0.36
    Activations Density 0.003%

    No Known Activations