© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39736
    Prev
    Next
    INDEX
    Explanations

    structural elements

    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_57_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
     <-
    1.02
    <-
    0.87
     ←
    0.86
     <--
    0.81
    ←
    0.79
     <<<
    0.76
    leftarrow
    0.73
    <<<
    0.73
     <<
    0.71
    
    0.68
    POSITIVE LOGITS
    whose
    0.53
     whose
    0.41
     thereby
    0.39
     sodass
    0.36
    ことで
    0.36
    ῃ
    0.35
    تقديم
    0.34
     bizi
    0.33
     определенных
    0.33
     established
    0.32
    Activations Density 0.364%

    No Known Activations