© 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. 127394
    Prev
    Next
    INDEX
    Explanations

    CCaaS / CC

    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
    ।
    0.95
     can
    0.88
     twórc
    0.80
     ricorda
    0.79
    نی
    0.78
    '।
    0.73
    。
    0.73
    ના
    0.73
    ני
    0.73
     poslov
    0.71
    POSITIVE LOGITS
    s
    1.00
    sd
    0.75
    sis
    0.70
    saga
    0.69
    sin
    0.69
    sed
    0.68
    r
    0.67
    maßnahmen
    0.66
    solvent
    0.65
    lls
    0.65
    Activations Density 0.001%

    No Known Activations