© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86092
    Prev
    Next
    INDEX
    Explanations

    all, both, every

    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_23_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
    𝓃
    0.37
    ﭜ
    0.35
    उ
    0.34
     Enrichment
    0.33
    ᠰ
    0.33
    conda
    0.33
     конди
    0.32
    Avg
    0.32
    poque
    0.32
    Conditional
    0.32
    POSITIVE LOGITS
     പക്ഷ
    0.35
     heated
    0.32
    فراد
    0.32
     contacting
    0.31
     suddenly
    0.29
     see
    0.28
     contacts
    0.28
     ><
    0.28
     ദേശ
    0.28
     research
    0.27
    Activations Density 0.003%

    No Known Activations