© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9428
    Prev
    Next
    INDEX
    Explanations

    making a point

    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
     Functions
    0.54
    ohm
    0.53
    breath
    0.52
    In
    0.51
    bs
    0.51
     Attention
    0.51
    ä
    0.51
    ik
    0.50
    ans
    0.50
     Minutes
    0.50
    POSITIVE LOGITS
    اليه
    0.61
     economici
    0.61
     zis
    0.59
     наличи
    0.59
    ِي
    0.58
    하자
    0.57
     él
    0.56
     apiUrl
    0.56
     fáb
    0.55
    ленного
    0.55
    Activations Density 0.059%

    No Known Activations