© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86384
    Prev
    Next
    INDEX
    Explanations

    illusion

    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_3_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
    a
    0.79
    :
    0.71
    it
    0.63
    rul
    0.62
    translation
    0.61
    their
    0.57
    ។
    0.57
    science
    0.57
    ":
    0.56
     الص
    0.55
    POSITIVE LOGITS
     unfl
    0.55
    स्ट
    0.51
    어졌
    0.51
    มี
    0.50
    ل
    0.50
     디
    0.50
     equated
    0.49
    取り
    0.49
    로
    0.49
    িখিত
    0.48
    Activations Density 0.000%

    No Known Activations