© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30249
    Prev
    Next
    INDEX
    Explanations

    formulas or calculations

    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_40_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
     Outer
    0.42
     Evan
    0.40
    餉
    0.40
     rotacao
    0.38
     주고
    0.37
     evoking
    0.37
     Sphere
    0.37
    AreaData
    0.37
     формула
    0.37
    欷
    0.35
    POSITIVE LOGITS
    allel
    0.44
    ibers
    0.44
    allele
    0.43
    Pil
    0.43
     Pil
    0.41
     tempat
    0.41
     Gesch
    0.40
    plt
    0.40
     volt
    0.39
    anio
    0.38
    Activations Density 0.009%

    No Known Activations