© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104730
    Prev
    Next
    INDEX
    Explanations

    html table data cell

    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_1_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
    ни
    1.79
    are
    1.46
    та
    1.37
    ре
    1.30
    ே
    1.29
    ла
    1.27
    вання
    1.23
    ی
    1.21
    к
    1.20
     efectivamente
    1.18
    POSITIVE LOGITS
    </h3>
    1.30
    1.23
    ↵
    1.20
    Content
    1.14
    。
    1.11
    App
    1.09
    </h4>
    1.09
    Ret
    1.07
    ↵↵↵
    1.06
    Quest
    1.06
    Activations Density 0.000%

    No Known Activations