© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92432
    Prev
    Next
    INDEX
    Explanations

    completion of work

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    guns
    0.33
    -">
    0.33
    kbd
    0.32
    ？](
    0.31
     ໜອງ
    0.30
    hdd
    0.30
    "("
    0.30
    barred
    0.29
    ίδα
    0.29
    <<"
    0.29
    POSITIVE LOGITS
    <strong>
    0.37
    <em>
    0.34
    จาก
    0.34
    W
    0.33
    를
    0.32
    สำหรับ
    0.32
    F
    0.31
    Last
    0.31
     continue
    0.30
     been
    0.30
    Activations Density 0.005%

    No Known Activations