© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202828
    Prev
    Next
    INDEX
    Explanations

    defender of

    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
    at
    1.71
    et
    1.45
    o
    1.34
    as
    1.33
    es
    1.32
    ere
    1.30
    ed
    1.27
    ell
    1.16
    ar
    1.15
    y
    1.14
    POSITIVE LOGITS
    ใน
    1.05
    س
    1.02
    ྥ
    1.00
    轳
    0.99
    بی
    0.97
    لی
    0.96
    мет
    0.96
    та
    0.96
    도
    0.94
    起こ
    0.93
    Activations Density 0.000%

    No Known Activations