© 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. 165725
    Prev
    Next
    INDEX
    Explanations

    <start_of_turn>

    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
    峋
    0.37
    签证
    0.36
     méthodique
    0.36
    PhotoImage
    0.35
    入境
    0.35
     डिवीजन
    0.34
    atifs
    0.34
     Beweg
    0.33
    과는
    0.33
    ামন্ত্রী
    0.33
    POSITIVE LOGITS
     sucking
    0.71
     sucked
    0.62
     sucks
    0.60
     suck
    0.59
    吸
    0.53
     suction
    0.47
     Suck
    0.45
     sucker
    0.44
     hút
    0.42
     吸
    0.42
    Activations Density 0.001%

    No Known Activations