© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 120730
    Prev
    Next
    INDEX
    Explanations

    password, gene, numbers, codes

    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_38_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
    rike
    0.40
    strated
    0.38
    汽车
    0.37
    ._
    0.36
     Mercedes
    0.36
     accred
    0.36
     Kwiatkowski
    0.36
     cevap
    0.36
    wicket
    0.36
     Kik
    0.35
    POSITIVE LOGITS
    slidesPer
    0.42
    料
    0.40
    Libraries
    0.39
    Virtual
    0.38
     ভার্চ
    0.38
     શેર
    0.38
    Rooms
    0.37
    帷
    0.37
     compartilh
    0.37
     spilling
    0.37
    Activations Density 0.000%

    No Known Activations