© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142619
    Prev
    Next
    INDEX
    Explanations

    clear driving

    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_46_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
    喉
    0.40
    িকর
    0.40
    Sn
    0.37
     ఇండి
    0.37
     इंड
    0.37
    சே
    0.37
     Phantom
    0.37
    assays
    0.37
    嚎
    0.37
    hang
    0.37
    POSITIVE LOGITS
     Driving
    0.50
     clara
    0.49
    明確
    0.46
     driving
    0.43
     modern
    0.43
     clearer
    0.42
     क्लियर
    0.42
     स्पष्ट
    0.41
    Driving
    0.40
     clear
    0.40
    Activations Density 0.000%

    No Known Activations