© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32134
    Prev
    Next
    INDEX
    Explanations

    set off

    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_7_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
     arbres
    0.33
     axles
    0.32
    ר
    0.32
    an
    0.31
     photons
    0.30
    ন
    0.30
     tolls
    0.30
    B
    0.30
    ar
    0.29
    न
    0.29
    POSITIVE LOGITS
    ili
    0.30
    river
    0.28
     in
    0.27
    í
    0.26
    rives
    0.25
    ama
    0.25
     सुरक्षित
    0.25
    imą
    0.25
    uksen
    0.25
    ζει
    0.25
    Activations Density 0.002%

    No Known Activations