© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32965
    Prev
    Next
    INDEX
    Explanations

    prof

    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
    तिक
    0.43
    োট
    0.41
    片
    0.41
    áci
    0.39
     textes
    0.38
    암
    0.38
    file
    0.38
    xSpeed
    0.38
    filenames
    0.37
    কলাপ
    0.37
    POSITIVE LOGITS
    ributive
    0.43
    β
    0.42
    護
    0.41
    ovo
    0.40
     apo
    0.40
     दिवा
    0.40
    <0xAA>
    0.39
     remedial
    0.38
     Milner
    0.38
    SERVICIO
    0.38
    Activations Density 0.008%

    No Known Activations