© 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. 143138
    Prev
    Next
    INDEX
    Explanations

    keep up

    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
    ти
    1.59
    ্ড
    1.48
    រ
    1.45
    يد
    1.35
    ╅
    1.15
    ivní
    1.13
    고
    1.13
     فريبي
    1.10
    র
    1.09
    ية
    1.09
    POSITIVE LOGITS
    ם
    1.73
    um
    1.65
    ق
    1.60
    ור
    1.53
    ad
    1.48
    ன்
    1.46
    ay
    1.44
    ob
    1.43
    un
    1.42
    ol
    1.41
    Activations Density 0.001%

    No Known Activations