© 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. 7076
    Prev
    Next
    INDEX
    Explanations

    app title and home

    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
    avalt
    0.43
    ابي
    0.40
    ))^{
    0.38
    ဖွ
    0.37
     सूफ़ी
    0.36
    强的
    0.36
    珉
    0.35
     দী
    0.35
    icals
    0.35
    +|\
    0.35
    POSITIVE LOGITS
     ৭৫
    0.42
    show
    0.40
    dark
    0.40
     show
    0.40
     Show
    0.40
     teat
    0.40
     NAV
    0.38
    รร
    0.37
    芓
    0.36
     Nau
    0.36
    Activations Density 0.002%

    No Known Activations