© 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. 231193
    Prev
    Next
    INDEX
    Explanations

    sure of

    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
     }.
    0.92
    姮
    0.91
    im
    0.91
    UN
    0.90
    س
    0.90
     ].
    0.89
     ?.
    0.88
    ിച്ച്
    0.85
     OS
    0.83
     €.
    0.82
    POSITIVE LOGITS
    ین
    1.30
    な
    1.13
    اری
    0.98
    е
    0.98
    কে
    0.97
    ید
    0.97
    )،
    0.94
    uje
    0.93
    یر
    0.92
    الی
    0.92
    Activations Density 0.000%

    No Known Activations