© 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. 179089
    Prev
    Next
    INDEX
    Explanations

    disclaimer text

    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
    sol
    0.42
    mites
    0.41
    v
    0.41
    restrial
    0.40
    prost
    0.40
    marine
    0.40
    arak
    0.38
    aiser
    0.38
    substrate
    0.38
    ມ
    0.37
    POSITIVE LOGITS
     Shirley
    0.42
     કરવું
    0.41
     देखा
    0.41
    рка
    0.40
    क्ती
    0.40
    ColorBit
    0.39
     STATIC
    0.38
     Connecticut
    0.38
     নুর
    0.38
    Tyler
    0.38
    Activations Density 0.006%

    No Known Activations