© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52539
    Prev
    Next
    INDEX
    Explanations

    code blocks with curly braces

    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_31_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
    }^{-}$,
    0.39
     ră
    0.38
     Nulla
    0.38
     پانی
    0.37
    కుంటు
    0.35
    roud
    0.34
    出一
    0.34
    дея
    0.34
    rothed
    0.34
    Introduceti
    0.34
    POSITIVE LOGITS
    ARGB
    0.42
    এছ
    0.42
     élo
    0.39
     species
    0.38
    Ī
    0.37
    ধারণ
    0.36
    ABI
    0.36
    ೪
    0.36
     incl
    0.36
     organism
    0.35
    Activations Density 0.015%

    No Known Activations