© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173253
    Prev
    Next
    INDEX
    Explanations

    newline character removal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
    is
    0.55
    de
    0.52
    au
    0.49
    guesses
    0.49
    it
    0.49
    as
    0.49
    é
    0.49
    am
    0.48
    Ir
    0.48
    ä
    0.48
    POSITIVE LOGITS
     finances
    0.48
     পাখির
    0.46
     Bakufu
    0.45
     financials
    0.45
     encoders
    0.45
     ቤ
    0.44
     qDebug
    0.44
    hanam
    0.43
     serializer
    0.43
     ఆర్థిక
    0.42
    Activations Density 0.002%

    No Known Activations