© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223252
    Prev
    Next
    INDEX
    Explanations

    javascript code components

    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_10_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
    at
    0.57
    ز
    0.51
    u
    0.48
    F
    0.48
    ER
    0.48
    of
    0.47
    0
    0.47
                    
    0.45
    یتی
    0.45
    জ
    0.45
    POSITIVE LOGITS
     snowflakes
    0.42
    la
    0.42
     reson
    0.42
    ring
    0.40
     skulls
    0.38
     ligaments
    0.38
     kvadr
    0.38
     frameworks
    0.38
    stes
    0.38
     Несмотря
    0.38
    Activations Density 0.001%

    No Known Activations