© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141246
    Prev
    Next
    INDEX
    Explanations

    Lean syntax constructs

    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_12_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
     Artin
    0.45
    수가
    0.44
     ಅರ್ಜಿ
    0.42
    수로
    0.42
    서트
    0.41
    魷
    0.41
    IRIS
    0.41
    עות
    0.40
    езда
    0.40
     oliva
    0.40
    POSITIVE LOGITS
     Doch
    0.45
     -"
    0.44
     limpi
    0.42
     inicio
    0.41
     Chief
    0.41
     People
    0.40
     separación
    0.39
    不过
    0.39
    ↵
    0.39
     हफ्ते
    0.39
    Activations Density 0.001%

    No Known Activations