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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164768
    Prev
    Next
    INDEX
    Explanations

    tpe relationship

    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_13_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
    s
    0.51
     वजह
    0.49
    組み立て
    0.46
    VILLE
    0.46
     күн
    0.46
    িস
    0.45
     zestaw
    0.45
    ствовали
    0.45
    ม
    0.45
    "?
    0.44
    POSITIVE LOGITS
    order
    0.59
    뷁
    0.56
    Particles
    0.55
    lipid
    0.55
    lers
    0.54
    remarks
    0.53
    waters
    0.53
    comments
    0.53
    wari
    0.53
    rents
    0.53
    Activations Density 0.000%

    No Known Activations