© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100686
    Prev
    Next
    INDEX
    Explanations

    negative reaction, emotion, perception

    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_16_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
    蝮
    0.31
    ramar
    0.28
    四大
    0.26
    *
    0.25
    uvial
    0.25
    คู่
    0.24
    odont
    0.24
    皮革
    0.24
    一天
    0.24
    umim
    0.24
    POSITIVE LOGITS
    こだ
    0.27
     ಜ
    0.25
    愫
    0.25
     यर
    0.24
     직
    0.24
     iterable
    0.24
     subspace
    0.24
    CharField
    0.24
    નો
    0.23
    גו
    0.23
    Activations Density 0.012%

    No Known Activations