© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52712
    Prev
    Next
    INDEX
    Explanations

    load model or dataset

    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_31_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
     Hayashi
    0.42
    牛奶
    0.39
    eer
    0.39
     milk
    0.36
    dish
    0.36
    hede
    0.35
    enetr
    0.35
    防
    0.35
    ้อมูล
    0.35
    हिम
    0.35
    POSITIVE LOGITS
    铷
    0.47
    <unused51>
    0.40
    달
    0.39
     pior
    0.38
     आये
    0.38
     MARKETING
    0.37
     Rubén
    0.36
    記者
    0.35
     LIABILITY
    0.35
     આવ્યા
    0.35
    Activations Density 0.005%

    No Known Activations