© 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. 36092
    Prev
    Next
    INDEX
    Explanations

    tuple

    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
     lí
    0.45
    Kong
    0.45
    kong
    0.44
    ý
    0.44
    FrameID
    0.43
     kong
    0.43
    Vod
    0.40
     კონ
    0.40
    yd
    0.40
     kon
    0.38
    POSITIVE LOGITS
     ту
    0.65
     Tu
    0.61
     tu
    0.57
     Tuple
    0.57
     tuple
    0.55
     TU
    0.55
     तु
    0.53
     tuples
    0.53
     투
    0.52
    tu
    0.52
    Activations Density 0.008%

    No Known Activations