© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34953
    Prev
    Next
    INDEX
    Explanations

    don't worry about

    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_3_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
    بە
    0.69
    dır
    0.68
    していない
    0.68
    ດ
    0.67
    in
    0.66
    ."),
    0.64
    textColor
    0.63
    눗
    0.63
    ması
    0.63
    isyen
    0.62
    POSITIVE LOGITS
    ুল
    0.66
    ier
    0.63
    om
    0.61
    })
    0.58
    ili
    0.57
    ik
    0.56
    man
    0.56
     Fluor
    0.56
     Professor
    0.55
    ib
    0.55
    Activations Density 0.002%

    No Known Activations