© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110080
    Prev
    Next
    INDEX
    Explanations

    D.C. bwave

    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
    2
    1.70
    ни
    1.40
    ur
    1.25
    ized
    1.15
    ция
    1.12
    ا
    1.10
    ről
    1.09
    ール
    1.03
    зки
    1.02
    ról
    1.02
    POSITIVE LOGITS
     it
    1.32
     do
    1.30
    P
    1.30
     compete
    1.28
     acab
    1.26
     confirm
    1.24
     by
    1.23
     paga
    1.20
     at
    1.20
     been
    1.14
    Activations Density 0.002%

    No Known Activations