© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145542
    Prev
    Next
    INDEX
    Explanations

    ชนิด devices

    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_0_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
    f
    1.79
    s
    1.73
    지
    1.70
    sk
    1.43
    ↵
    1.38
    that
    1.34
    ியா
    1.31
    。
    1.30
    ्स
    1.28
    sa
    1.28
    POSITIVE LOGITS
    ৫
    1.69
    ని
    1.38
    ول
    1.30
    ua
    1.20
     thiab
    1.20
    ৬
    1.15
     be
    1.13
    ৮
    1.13
    ));
    1.11
     dhe
    1.10
    Activations Density 0.000%

    No Known Activations