© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 211519
    Prev
    Next
    INDEX
    Explanations

    tourist attractions

    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_43_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
     veins
    0.46
    ༡
    0.43
     Cream
    0.43
    Cream
    0.41
    និច
    0.41
    Moh
    0.40
     Moh
    0.38
    丵
    0.38
    वरों
    0.38
     Become
    0.38
    POSITIVE LOGITS
     confident
    0.43
     confidently
    0.40
     পাট
    0.38
    luss
    0.35
    Confident
    0.35
    confident
    0.34
     पाट
    0.34
    Pal
    0.34
     Па
    0.34
     bred
    0.34
    Activations Density 0.000%

    No Known Activations