© 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. 216052
    Prev
    Next
    INDEX
    Explanations

    rotate through stations

    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
     табы
    0.38
    之下
    0.35
    concatenate
    0.33
    ometri
    0.33
    싯
    0.32
    ヴ
    0.32
     Und
    0.32
     adjustable
    0.32
     underscores
    0.32
    CET
    0.32
    POSITIVE LOGITS
     station
    0.56
     stations
    0.53
    Station
    0.50
    station
    0.46
     станции
    0.46
     estaciones
    0.46
     Station
    0.44
     estación
    0.44
    stations
    0.44
    站
    0.43
    Activations Density 0.001%

    No Known Activations