© 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
    2. Gemma-3-27B-IT
    3. 47-GEMMASCOPE-2-TRANSCODER-262K
    4. 216519
    Prev
    Next
    INDEX
    Explanations

    abuse

    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_47_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
    ᓯ
    0.42
     গোলা
    0.41
    ounded
    0.40
     温
    0.38
     regener
    0.38
    💡
    0.38
     rounded
    0.36
     chest
    0.36
    SDS
    0.36
     pInBuffer
    0.35
    POSITIVE LOGITS
    FieldError
    0.39
    logram
    0.39
    uettes
    0.38
    otional
    0.37
    грам
    0.36
    FileReader
    0.36
    ರಿ
    0.36
     放
    0.36
    ণিক
    0.35
    ankind
    0.35
    Activations Density 0.006%

    No Known Activations