© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 195145
    Prev
    Next
    INDEX
    Explanations

    production and producers

    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_9_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
     to
    0.48
    ای
    0.44
    0
    0.44
     perdu
    0.41
     थोड़ा
    0.41
     foment
    0.40
     novi
    0.40
     questi
    0.40
     maiores
    0.39
     daly
    0.39
    POSITIVE LOGITS
    ار
    0.48
    t
    0.44
    ми
    0.42
    s
    0.41
    tà
    0.40
    지만
    0.39
    í
    0.39
    ge
    0.38
    ية
    0.38
    عي
    0.37
    Activations Density 0.003%

    No Known Activations