© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200919
    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_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
    ول
    1.30
    ت
    1.10
    ح
    1.09
    ية
    1.02
    াল
    1.02
    üşt
    0.96
    ת
    0.96
    غ
    0.95
    ัน
    0.92
    نت
    0.92
    POSITIVE LOGITS
    don
    1.15
    das
    0.98
    die
    0.96
    oted
    0.95
    elling
    0.89
    म
    0.88
    that
    0.87
    who
    0.86
    How
    0.86
    ella
    0.85
    Activations Density 0.000%

    No Known Activations