© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43541
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Batterie
    0.57
     gehen
    0.51
     bieg
    0.51
     శ్రీ
    0.50
     ziehen
    0.50
     Batter
    0.49
    语音
    0.49
    泂
    0.49
    श्री
    0.49
     batterie
    0.49
    POSITIVE LOGITS
     तया
    0.57
    )».
    0.48
    ਉਣ
    0.43
    offs
    0.43
     Consistent
    0.42
    <0xA5>
    0.42
     вод
    0.42
    ಗಾರ
    0.41
     नोन
    0.41
     помі
    0.41
    Activations Density 0.000%

    No Known Activations