© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260734
    Prev
    Next
    INDEX
    Explanations

    Wizard, spir, 灵

    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_5_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
    ре
    1.46
    بي
    1.45
    イ
    1.38
    ü
    1.37
    س
    1.33
    લ
    1.27
    ル
    1.25
    ロ
    1.25
    리
    1.25
    비
    1.25
    POSITIVE LOGITS
    ↵
    1.39
    in
    1.30
    ene
    1.22
    -
    1.22
    iden
    1.09
    _
    1.05
     can
    1.04
    en
    1.03
    ida
    1.01
     dalam
    0.99
    Activations Density 0.001%

    No Known Activations