© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150687
    Prev
    Next
    INDEX
    Explanations

    given the

    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_23_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
    iteks
    0.43
    즈
    0.43
     recommending
    0.41
     consigli
    0.41
    殁
    0.40
    ssid
    0.40
    скет
    0.39
    nsics
    0.39
     مدی
    0.39
    係る
    0.39
    POSITIVE LOGITS
    constant
    0.36
    更新
    0.36
    Gamma
    0.35
    δ
    0.35
    thym
    0.35
     δ
    0.34
    หน้า
    0.34
     σ
    0.33
    ทุกคน
    0.33
     весь
    0.33
    Activations Density 0.013%

    No Known Activations