© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5070
    Prev
    Next
    INDEX
    Explanations

    combinations formula

    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_40_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
     kullanım
    0.49
    ゔ
    0.42
     사용할
    0.41
    hattim
    0.40
    𒄑
    0.40
     использует
    0.39
     మన
    0.39
     नियंत्रण
    0.38
     decking
    0.38
    вою
    0.38
    POSITIVE LOGITS
    清
    0.42
    無視
    0.41
     ignored
    0.38
    Ignoring
    0.38
    plicity
    0.38
     ignoring
    0.38
    Claire
    0.38
    ┤
    0.38
     clear
    0.37
     simplify
    0.37
    Activations Density 0.001%

    No Known Activations