© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10514
    Prev
    Next
    INDEX
    Explanations

    ASCII art structures

    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_13_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
    车
    0.44
     музей
    0.43
     جمعه
    0.42
    ش
    0.41
    Australia
    0.41
    અ
    0.41
    Fellow
    0.41
    玠
    0.40
    INGLE
    0.40
     सेमीफाइनल
    0.40
    POSITIVE LOGITS
    spacePad
    0.47
    haltung
    0.45
    тке
    0.45
    γγρα
    0.45
     alcanzar
    0.41
     Ferté
    0.41
     parturient
    0.41
     voordat
    0.41
    gradation
    0.40
     postpartum
    0.39
    Activations Density 0.030%

    No Known Activations