© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167699
    Prev
    Next
    INDEX
    Explanations

    when

    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_56_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
    ตอน
    0.44
     {}>,
    0.35
    ぞれ
    0.32
    rimp
    0.32
    acrylamide
    0.32
    agini
    0.31
     ตอน
    0.31
     Bereits
    0.31
    攫
    0.31
    anting
    0.30
    POSITIVE LOGITS
    当
    3.09
    當
    2.86
     when
    2.55
    when
    2.50
     когда
    2.45
     当
    2.45
    เมื่อ
    2.31
     當
    2.31
     cuando
    2.27
     quando
    2.27
    Activations Density 0.001%

    No Known Activations