© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 104134
    Prev
    Next
    INDEX
    Explanations

    apply

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     slto
    0.38
     Larn
    0.37
    伐
    0.37
    벌
    0.36
    ilha
    0.35
     autó
    0.34
    ว่าเป็น
    0.34
    ｪ
    0.34
    Laurent
    0.33
    ლებ
    0.32
    POSITIVE LOGITS
     apply
    2.50
     applying
    2.47
    apply
    2.39
    Applying
    2.38
    Apply
    2.36
     applies
    2.33
     Apply
    2.33
     Applying
    2.31
    applying
    2.27
     applied
    2.23
    Activations Density 0.393%

    No Known Activations