© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45204
    Prev
    Next
    INDEX
    Explanations

    URLs and web addresses

    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_13_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
    ein
    0.55
    íng
    0.54
    த்தார்
    0.53
    ır
    0.52
    琪
    0.52
    🔸
    0.52
     در
    0.52
    Ề
    0.52
     dari
    0.50
    ía
    0.50
    POSITIVE LOGITS
     conclude
    0.56
     finalize
    0.54
     babys
    0.54
     immobilized
    0.53
     organism
    0.52
     Б
    0.52
     demonstrate
    0.52
     традиции
    0.51
    organisms
    0.50
     legalize
    0.50
    Activations Density 0.156%

    No Known Activations