© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52451
    Prev
    Next
    INDEX
    Explanations

    URLs to people's pages

    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_30_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
     Tuscany
    0.35
    发生在
    0.34
    axiom
    0.33
     Frauen
    0.33
    darwin
    0.33
    </tfoot>
    0.32
     miracle
    0.32
    vit
    0.32
    ்து
    0.32
     paradigms
    0.32
    POSITIVE LOGITS
     División
    0.43
     Гар
    0.41
    ज्यो
    0.40
     ज्ञ
    0.39
     initialized
    0.38
    ULTY
    0.37
     اللغة
    0.37
    ledged
    0.36
     වශ
    0.36
    㚐
    0.36
    Activations Density 0.000%

    No Known Activations