© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18229
    Prev
    Next
    INDEX
    Explanations

    conflict

    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_15_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
     игровые
    0.28
    \%,
    0.26
    媜
    0.26
     мы
    0.25
     pertinente
    0.25
    следования
    0.25
     Саме
    0.25
    èche
    0.25
     एम
    0.24
     nỗi
    0.24
    POSITIVE LOGITS
    at
    0.28
     luminosity
    0.27
     deplete
    0.26
    withtag
    0.25
    not
    0.25
    omponent
    0.25
    or
    0.24
    orate
    0.24
    玳
    0.24
    是个
    0.24
    Activations Density 0.055%

    No Known Activations