© 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. 31674
    Prev
    Next
    INDEX
    Explanations

    tells

    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
    讓人
    0.44
    让人
    0.42
     mám
    0.42
    Meu
    0.39
    you
    0.39
    अफ
    0.37
    áb
    0.36
    詮
    0.36
    wb
    0.36
     للس
    0.36
    POSITIVE LOGITS
     tell
    0.82
     tells
    0.78
     telling
    0.77
     Tell
    0.74
    告訴
    0.71
     told
    0.70
    告诉
    0.69
     Tells
    0.67
     Telling
    0.66
    Tell
    0.64
    Activations Density 0.437%

    No Known Activations