© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210557
    Prev
    Next
    INDEX
    Explanations

    south-eastern, south-western, north-eastern, north-western

    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_5_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
    .
    1.98
    리
    1.36
    .。
    1.33
    на
    1.21
    나
    1.20
    ர
    1.18
    ना
    1.15
    नी
    1.15
    ー
    1.12
    서
    1.12
    POSITIVE LOGITS
     and
    1.52
    0
    1.25
    lty
    1.13
     of
    1.12
    ja
    1.08
    mma
    1.05
    आती
    1.03
    '))
    1.00
    lte
    1.00
    '
    0.97
    Activations Density 0.000%

    No Known Activations