© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204794
    Prev
    Next
    INDEX
    Explanations

    without being

    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_6_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
    ח
    1.20
    ב
    1.04
    מ
    1.02
    =\
    0.95
    ้
    0.95
    ā
    0.95
    ூ
    0.93
    هم
    0.91
     to
    0.88
    0
    0.87
    POSITIVE LOGITS
    s
    1.27
     IQR
    0.84
    наче
    0.82
    ሶች
    0.80
     attham
    0.80
     ermög
    0.78
     sabbam
    0.78
     způ
    0.77
     kammam
    0.77
     WebDriver
    0.76
    Activations Density 0.002%

    No Known Activations