© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139050
    Prev
    Next
    INDEX
    Explanations

    то

    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_46_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
     Pearson
    0.43
     ¬
    0.40
     فن
    0.39
    Titles
    0.39
    Pearson
    0.38
    стой
    0.38
    ChatGPT
    0.37
     Tis
    0.37
     タイ
    0.37
    anakk
    0.37
    POSITIVE LOGITS
    layer
    0.43
    পের
    0.43
    紝
    0.42
    色的
    0.40
    reten
    0.39
     Layer
    0.39
    detector
    0.39
     layer
    0.38
    ீரல்
    0.38
    reat
    0.38
    Activations Density 0.000%

    No Known Activations