© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 37-GEMMASCOPE-2-TRANSCODER-262K
    4. 136763
    Prev
    Next
    INDEX
    Explanations

    species extinction

    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_37_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
     tacos
    0.82
     taco
    0.81
     Taco
    0.74
     tac
    0.56
    🌮
    0.55
     Tac
    0.48
     Tacoma
    0.47
    acos
    0.46
     TAC
    0.44
    Tac
    0.43
    POSITIVE LOGITS
    nesi
    0.40
    秥
    0.40
     উদ্যোগ
    0.38
     straws
    0.38
    ندس
    0.38
     നെ
    0.37
     যাহা
    0.37
     chips
    0.36
     batted
    0.36
    茏
    0.36
    Activations Density 0.005%

    No Known Activations