© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32869
    Prev
    Next
    INDEX
    Explanations

    linked list node declarations

    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_31_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
     trivially
    0.42
    зяй
    0.41
     جال
    0.37
     goals
    0.37
    amiya
    0.36
     хозяй
    0.35
     okay
    0.35
    坎
    0.35
    ẫ
    0.34
    技巧
    0.34
    POSITIVE LOGITS
    AB
    0.38
    Architecture
    0.38
    Auto
    0.36
    盤
    0.36
    Fall
    0.35
     Falcons
    0.35
     који
    0.35
    Adv
    0.35
     Alloc
    0.35
    Deliver
    0.35
    Activations Density 0.032%

    No Known Activations