© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60189
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ون
    1.82
     on
    1.65
    r
    1.54
    ל
    1.54
    the
    1.49
    ل
    1.49
    w
    1.46
    리
    1.44
    ان
    1.41
    ні
    1.41
    POSITIVE LOGITS
    -
    0.99
     koul
    0.97
    ća
    0.93
     have
    0.91
     základ
    0.89
    ação
    0.88
    ↵
    0.86
     niż
    0.86
    습니다
    0.84
     يا
    0.84
    Activations Density 0.000%

    No Known Activations