© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    4. 90826
    Prev
    Next
    INDEX
    Explanations

    fort

    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
    τε
    0.44
    cknow
    0.42
     etter
    0.42
     fervor
    0.40
     wenn
    0.40
     лінії
    0.39
    scribe
    0.39
     ձ
    0.39
     дані
    0.38
     серпня
    0.38
    POSITIVE LOGITS
    yó
    0.54
    yi
    0.47
    yaf
    0.41
    yon
    0.40
    ilos
    0.40
    yam
    0.40
    formas
    0.39
    yil
    0.39
     внутрен
    0.38
    iguo
    0.38
    Activations Density 0.002%

    No Known Activations