© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45359
    Prev
    Next
    INDEX
    Explanations

    archway

    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_3_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
    agment
    0.60
     archive
    0.59
     apie
    0.57
    angnya
    0.55
    archive
    0.55
    I
    0.55
     archival
    0.54
     लग
    0.54
     langt
    0.54
    angk
    0.53
    POSITIVE LOGITS
     as
    0.82
    ل
    0.79
    ↵
    0.77
    ル
    0.69
    ল
    0.67
    ल
    0.67
     טוב
    0.66
    س
    0.63
    are
    0.63
    dio
    0.63
    Activations Density 0.000%

    No Known Activations