© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40163
    Prev
    Next
    INDEX
    Explanations

    F

    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_11_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
     Marius
    0.58
     jurídico
    0.58
    ర్యా
    0.57
    ด
    0.53
    დეს
    0.52
    ÕES
    0.52
    യുള്ള
    0.51
    ificado
    0.50
    ەر
    0.50
    千年
    0.50
    POSITIVE LOGITS
     r
    0.72
     stimulants
    0.70
     matchups
    0.69
     rockets
    0.67
     aunts
    0.66
     чем
    0.66
     khaki
    0.64
     downturn
    0.64
     stressors
    0.64
     veal
    0.63
    Activations Density 0.000%

    No Known Activations