© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22909
    Prev
    Next
    INDEX
    Explanations

    Code execution starts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    开
    1.46
    開
    1.34
    $\
    1.19
     开
    1.15
     $\
    1.08
     開
    0.96
     khai
    0.93
     Opening
    0.82
    开了
    0.80
     opening
    0.79
    POSITIVE LOGITS
    """,
    0.43
    ições
    0.36
    லாமல்
    0.34
    ":"",
    0.34
     dus
    0.34
    仹
    0.33
    प्शन
    0.33
    वण्यासाठी
    0.33
    ';...
    0.33
    amless
    0.32
    Activations Density 0.018%

    No Known Activations