© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201492
    Prev
    Next
    INDEX
    Explanations

    substrate influence

    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_6_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
    。
    1.18
    ي
    1.16
    i
    1.16
     programmi
    1.02
    י
    1.02
    ।
    0.96
    يته
    0.96
    ين
    0.94
    которы
    0.92
    3
    0.90
    POSITIVE LOGITS
    ↵↵
    1.09
    я
    0.88
     există
    0.84
     câteva
    0.79
    一つの
    0.77
     îi
    0.77
    一定的
    0.75
     எதுவும்
    0.74
     هستند
    0.73
     exceeding
    0.73
    Activations Density 0.000%

    No Known Activations