© 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. 159113
    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
    h
    1.65
    л
    1.55
    з
    1.44
    б
    1.21
    и
    1.20
    य
    1.16
    ז
    1.16
    ст
    1.14
    й
    1.13
    و
    1.13
    POSITIVE LOGITS
    ’
    1.14
    ాన్ని
    1.09
    یی
    1.05
    ncnc
    1.04
    s
    0.98
     misinterpreted
    0.97
    혔
    0.95
    daily
    0.94
    tedir
    0.93
    dı
    0.91
    Activations Density 0.000%

    No Known Activations