© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202903
    Prev
    Next
    INDEX
    Explanations

    screen class endings

    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
    GK
    0.42
    ⌀
    0.41
    য়
    0.40
    acon
    0.38
    бро
    0.38
    čak
    0.37
    genc
    0.37
    Contra
    0.37
    vio
    0.36
    ACON
    0.36
    POSITIVE LOGITS
     końca
    0.42
     끝
    0.42
     نهاية
    0.41
     end
    0.41
    끝
    0.39
     Los
    0.38
     نصی
    0.38
     sfâr
    0.38
     sajana
    0.38
     نهايه
    0.37
    Activations Density 0.000%

    No Known Activations