© 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. 215950
    Prev
    Next
    INDEX
    Explanations

    SQL keywords

    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
     index
    0.43
     Rabbit
    0.39
    यों
    0.38
    咩
    0.37
     indices
    0.37
    ிகளை
    0.37
    enças
    0.36
     orig
    0.35
     aux
    0.35
     idx
    0.35
    POSITIVE LOGITS
    nict
    0.41
    platin
    0.40
    บั
    0.40
     neemt
    0.38
    ྕ
    0.38
    codone
    0.37
    cini
    0.37
    owiada
    0.37
    omeres
    0.36
    abela
    0.36
    Activations Density 0.006%

    No Known Activations