© 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. 145870
    Prev
    Next
    INDEX
    Explanations

    Renaissance

    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
    ;
    1.81
    t
    1.62
    x
    1.44
    p
    1.38
    g
    1.32
    the
    1.29
    c
    1.28
    y
    1.26
    dengan
    1.23
     andando
    1.22
    POSITIVE LOGITS
    리
    1.32
    它
    1.22
    設定
    1.20
    榜
    1.13
    では
    1.09
    ी
    1.08
    نگ
    1.07
    RestTemplate
    1.06
    려
    1.03
    It
    1.02
    Activations Density 0.000%

    No Known Activations