© 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. 43270
    Prev
    Next
    INDEX
    Explanations

    Pro Max

    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
    ద
    0.64
    jší
    0.64
    ci
    0.60
    na
    0.59
    กับ
    0.59
    Outlet
    0.57
    ssä
    0.55
    在
    0.55
     to
    0.54
    lines
    0.54
    POSITIVE LOGITS
     artistique
    0.75
     tenue
    0.74
     miljoen
    0.69
     brzo
    0.69
     devenit
    0.67
     اخرى
    0.66
     gdje
    0.65
     hvil
    0.65
     أ
    0.64
     soldats
    0.64
    Activations Density 0.006%

    No Known Activations