© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200104
    Prev
    Next
    INDEX
    Explanations

    wouldn't trade/rush/believe

    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_12_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
    伟大
    0.36
    ায়ক
    0.35
    ك
    0.35
    栻
    0.35
    各
    0.34
    was
    0.34
     apertures
    0.33
    ει
    0.33
     SIE
    0.33
    ᆸ
    0.32
    POSITIVE LOGITS
    9
    0.41
    1
    0.39
    しますが
    0.39
    7
    0.39
     ज्यादा
    0.38
    ari
    0.38
    బ్యా
    0.38
    可通过
    0.37
    _
    0.37
    فير
    0.36
    Activations Density 0.001%

    No Known Activations