© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    4. 159183
    Prev
    Next
    INDEX
    Explanations

    URL parsing or parameters

    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_2_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
    y
    1.69
    g
    1.60
    x
    1.50
    at
    1.45
    is
    1.39
     I
    1.31
    and
    1.24
    ه
    1.23
    a
    1.17
    it
    1.13
    POSITIVE LOGITS
     inférieure
    1.20
     ennemis
    1.20
     independente
    1.16
     indépend
    1.16
     конферен
    1.14
     énorm
    1.14
     iniz
    1.13
     azienda
    1.13
     entreprise
    1.13
     εται
    1.12
    Activations Density 0.001%

    No Known Activations