© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131334
    Prev
    Next
    INDEX
    Explanations

    "Did you know" facts

    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_50_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
    EM
    0.36
    ര
    0.33
    ITCH
    0.33
     प्लेइंग
    0.33
    ეფ
    0.33
    FM
    0.32
     ग्लूको
    0.32
    㻁
    0.32
    ECON
    0.32
    ܐ
    0.32
    POSITIVE LOGITS
     hab
    0.40
     avert
    0.40
     kaki
    0.39
    Ь
    0.38
     bri
    0.38
     tolle
    0.37
     h
    0.36
     nove
    0.36
    miri
    0.36
     contempl
    0.35
    Activations Density 0.000%

    No Known Activations