© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82226
    Prev
    Next
    INDEX
    Explanations

    you

    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
     is
    1.34
    og
    1.28
     a
    1.27
    </h3>
    1.26
    </b>
    1.25
    }$
    1.23
    1.23
    ong
    1.21
    ile
    1.17
     你
    1.16
    POSITIVE LOGITS
    ل
    1.55
    (
    1.44
    感じる
    1.33
    ي
    1.32
    用い
    1.27
    '
    1.26
    ０
    1.21
    $'
    1.19
    یی
    1.18
    開設
    1.18
    Activations Density 0.001%

    No Known Activations