© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6407
    Prev
    Next
    INDEX
    Explanations

    finite and infinite

    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_39_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
     giấc
    0.43
     карти
    0.41
     Шо
    0.40
     Schuster
    0.39
    CapsLock
    0.39
    锁
    0.39
     स्‍टार
    0.36
    宠
    0.36
     flattered
    0.36
    メラ
    0.36
    POSITIVE LOGITS
    궐
    0.41
     antip
    0.39
     zbior
    0.38
     asn
    0.38
    ially
    0.37
     immutable
    0.36
     DMR
    0.36
    volt
    0.35
    orting
    0.35
     entornos
    0.35
    Activations Density 0.009%

    No Known Activations