© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 526
    Prev
    Next
    INDEX
    Explanations

    function parentheses

    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_40_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
    收取
    0.41
    太平
    0.36
    ">/</
    0.35
     المهم
    0.35
    咥
    0.35
    cesa
    0.34
    戽
    0.34
    سلم
    0.34
     Ανακτήθηκε
    0.34
     asent
    0.33
    POSITIVE LOGITS
    ਾਸ
    0.40
     vows
    0.37
     employs
    0.37
    Kings
    0.36
    StringUtils
    0.36
    ஔ
    0.36
     முடிய
    0.36
    शाही
    0.35
    Sen
    0.35
    GOR
    0.35
    Activations Density 0.059%

    No Known Activations