© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13082
    Prev
    Next
    INDEX
    Explanations

    7B parameter models

    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_40_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
     Four
    0.39
    欝
    0.38
     onward
    0.37
     hora
    0.35
    ्रय
    0.35
    ierne
    0.35
     Ong
    0.34
     आगे
    0.34
     घंटा
    0.34
    Four
    0.33
    POSITIVE LOGITS
    सात
    0.46
    DAYS
    0.46
    七
    0.44
     séptimo
    0.43
    days
    0.42
    acqu
    0.42
     days
    0.42
    preds
    0.41
     ஏழு
    0.41
    ۷
    0.41
    Activations Density 0.021%

    No Known Activations