© 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. 228133
    Prev
    Next
    INDEX
    Explanations

    hin and dazu

    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_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
    在
    1.23
    ও
    1.07
    في
    1.02
    С
    1.02
    de
    0.95
    vět
    0.93
    も
    0.92
    da
    0.91
     Moż
    0.91
    ба
    0.91
    POSITIVE LOGITS
     on
    0.98
    ence
    0.95
    ă
    0.94
    েও
    0.93
    ਾ
    0.93
     for
    0.91
     entreprise
    0.91
    한
    0.88
    ↵↵
    0.88
     of
    0.88
    Activations Density 0.000%

    No Known Activations