© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49458
    Prev
    Next
    INDEX
    Explanations

    optional

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    Default
    0.29
    necessary
    0.27
    Bern
    0.25
    쩌
    0.25
     가지고
    0.25
    История
    0.25
     hiszen
    0.25
    不到
    0.24
    Someone
    0.24
    गौरतलब
    0.24
    POSITIVE LOGITS
     striis
    0.30
     saper
    0.28
    郘
    0.27
     scaling
    0.27
     HIIT
    0.26
     densidad
    0.26
    dumbbell
    0.25
     élément
    0.25
     нер
    0.25
     antigos
    0.25
    Activations Density 0.004%

    No Known Activations