© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84301
    Prev
    Next
    INDEX
    Explanations

    `myt` / `myd` / `mym` followed by common suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    ↵
    1.77
    ERS
    1.36
    А
    1.34
    Я
    1.32
                    
    1.20
    ↵↵
    1.19
    Q
    1.19
    O
    1.16
    的设计
    1.16
    Ε
    1.16
    POSITIVE LOGITS
    us
    2.39
    as
    2.34
    os
    2.06
    et
    1.99
    ção
    1.83
    ul
    1.77
    ся
    1.61
    った
    1.60
    و
    1.59
    on
    1.57
    Activations Density 0.000%

    No Known Activations