© 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. 162006
    Prev
    Next
    INDEX
    Explanations

    as a person

    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
    ө
    0.31
     kip
    0.30
    StarService
    0.29
    addressed
    0.29
    暦
    0.29
     fervor
    0.29
     обязательно
    0.29
    MemberList
    0.29
    ἧ
    0.28
    永遠
    0.28
    POSITIVE LOGITS
     트
    0.30
     unofficial
    0.30
     Anita
    0.29
    这样一个
    0.29
     Elizabeth
    0.29
     Elsie
    0.28
     Mysterious
    0.28
     וש
    0.28
     Battles
    0.28
     She
    0.28
    Activations Density 0.003%

    No Known Activations