© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202658
    Prev
    Next
    INDEX
    Explanations

    Strand Standard or Magazine

    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_37_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
     rope
    0.73
    繩
    0.66
     Rope
    0.65
     ropes
    0.63
     slings
    0.61
    绳
    0.60
     रस्सी
    0.57
    rope
    0.53
     rigging
    0.50
     sheaves
    0.50
    POSITIVE LOGITS
    谈判
    0.41
    apuram
    0.39
     polar
    0.38
    actin
    0.37
     nourishing
    0.36
    恆
    0.36
    attu
    0.36
     wade
    0.36
    agar
    0.36
     txtbtn
    0.35
    Activations Density 0.012%

    No Known Activations