© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122063
    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_3_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
    _
    0.90
    B
    0.88
    __
    0.80
    २
    0.74
    ૫
    0.74
    然后
    0.73
    %
    0.73
    어
    0.73
    Ş
    0.72
    J
    0.71
    POSITIVE LOGITS
    ud
    0.69
    at
    0.68
    er
    0.64
    ारा
    0.64
    history
    0.63
    helix
    0.62
    व
    0.62
    iel
    0.60
    iros
    0.60
    onerror
    0.59
    Activations Density 0.000%

    No Known Activations