© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 91082
    Prev
    Next
    INDEX
    Explanations

    encapsulated

    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_60_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
    在
    0.66
    ใน
    0.61
     in
    0.57
     в
    0.54
     في
    0.52
     σε
    0.48
     thriving
    0.45
     در
    0.40
    在上
    0.40
     fisc
    0.39
    POSITIVE LOGITS
     into
    0.62
    into
    0.61
    Into
    0.54
    到
    0.50
     Into
    0.48
     INTO
    0.45
    onto
    0.44
    യിലേക്ക്
    0.44
    戌
    0.43
    covering
    0.41
    Activations Density 0.008%

    No Known Activations