© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120516
    Prev
    Next
    INDEX
    Explanations

    emphasis markers

    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_27_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
     gamb
    0.31
     gamble
    0.31
     palo
    0.30
     cover
    0.29
     Mostly
    0.29
     baixo
    0.29
     arc
    0.28
    喺
    0.28
     dentro
    0.26
     within
    0.26
    POSITIVE LOGITS
    enteri
    0.32
    Outcome
    0.28
    준다
    0.27
    outcome
    0.26
    బడు
    0.26
     Compu
    0.26
    اگ
    0.25
    㬹
    0.25
     Федера
    0.25
    ก
    0.25
    Activations Density 0.002%

    No Known Activations