© 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. 244827
    Prev
    Next
    INDEX
    Explanations

    authentic and famous food descriptions

    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
     pretty
    0.41
     wind
    0.40
    ኸ
    0.38
    mongoUrl
    0.38
     Wind
    0.38
     lovely
    0.37
     wouldn
    0.37
     theater
    0.37
     elit
    0.37
     Wouldn
    0.37
    POSITIVE LOGITS
     попробовать
    0.55
     Authentic
    0.46
    これらの
    0.42
    Authent
    0.41
    ลอง
    0.41
     authenticity
    0.41
    嚐
    0.41
     authentic
    0.40
    Tried
    0.40
     ov
    0.40
    Activations Density 0.001%

    No Known Activations