© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170805
    Prev
    Next
    INDEX
    Explanations

    transient emotions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    反
    0.82
    的反
    0.68
    Int
    0.61
     Int
    0.55
     反
    0.53
     반
    0.50
    Reverse
    0.50
     Reverse
    0.47
     reverse
    0.46
    reverse
    0.46
    POSITIVE LOGITS
     intros
    0.72
     introspection
    0.68
    introspection
    0.54
     ಅಧಿಕ
    0.38
     দিবার
    0.38
     hers
    0.38
     importe
    0.36
    ехали
    0.36
    腧
    0.35
    获
    0.35
    Activations Density 0.000%

    No Known Activations