© 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. 130597
    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
    em
    1.38
    '
    1.14
     for
    1.08
    et
    1.06
    us
    0.99
    er
    0.98
    ist
    0.96
    o
    0.95
    కి
    0.88
    他
    0.88
    POSITIVE LOGITS
    ก่อน
    0.96
    غیر
    0.96
    ння
    0.96
    ."],
    0.96
    )$,
    0.94
    \}.
    0.92
    ]".
    0.90
     예정
    0.90
     ۳
    0.89
     आहे
    0.88
    Activations Density 0.000%

    No Known Activations