© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206820
    Prev
    Next
    INDEX
    Explanations

    winner advances or is chosen

    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_25_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
     disqualify
    0.34
     fortr
    0.31
     อนุ
    0.30
    溯
    0.29
    処理
    0.28
    vise
    0.27
     fum
    0.27
     quinoa
    0.27
     kilow
    0.27
    وفة
    0.27
    POSITIVE LOGITS
    rell
    0.32
    巻
    0.31
     Face
    0.30
    face
    0.29
     தினம்
    0.29
    Face
    0.29
     अफेयर
    0.28
     Sprach
    0.28
     വര്‍ഷ
    0.28
    тием
    0.28
    Activations Density 0.001%

    No Known Activations