© 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. 90102
    Prev
    Next
    INDEX
    Explanations

    nothing but

    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
     a
    0.71
     с
    0.70
     безопас
    0.70
     αλλά
    0.70
     but
    0.69
     אבל
    0.66
     компакт
    0.66
     сал
    0.65
     ло
    0.64
     $
    0.64
    POSITIVE LOGITS
    éma
    0.56
    শিক্ষা
    0.55
    Í
    0.54
     Struktur
    0.53
    🤵
    0.52
    isting
    0.50
    ⏪
    0.50
    era
    0.50
     Pflanzen
    0.49
    CTE
    0.48
    Activations Density 0.001%

    No Known Activations