© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18535
    Prev
    Next
    INDEX
    Explanations

    visual phenomena

    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_34_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
     \...
    0.37
    。...
    0.36
     bitmap
    0.35
    ▷
    0.35
    賠
    0.34
    ૧
    0.33
    ᐈ
    0.33
    ...+
    0.32
     stockbild
    0.32
     pera
    0.32
    POSITIVE LOGITS
    ញ្
    0.40
     환
    0.35
     रिक्
    0.33
     Ski
    0.33
    हिर
    0.33
     drops
    0.32
    स्टैंड
    0.32
     rind
    0.32
    guin
    0.32
    жду
    0.32
    Activations Density 0.008%

    No Known Activations