© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38506
    Prev
    Next
    INDEX
    Explanations

    param

    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_57_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
    ming
    0.45
    प्‍
    0.41
    ӓ
    0.41
    pena
    0.40
    miš
    0.39
    Ow
    0.38
    de
    0.38
    ba
    0.38
    ອງ
    0.38
    Facts
    0.38
    POSITIVE LOGITS
    នេះ
    0.38
     noise
    0.37
     PH
    0.37
     inl
    0.37
     doba
    0.37
    l
    0.36
    <unused40>
    0.35
     প্রেক্ষিতে
    0.35
    𓏧
    0.35
     Institutional
    0.35
    Activations Density 0.000%

    No Known Activations