© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13491
    Prev
    Next
    INDEX
    Explanations

    code blocks using `with`

    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_40_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
    Lion
    0.44
     Lions
    0.42
     Lion
    0.42
    british
    0.41
    British
    0.40
    獅
    0.40
    lion
    0.38
    Drop
    0.38
    drop
    0.38
    lions
    0.38
    POSITIVE LOGITS
    骛
    0.42
     найден
    0.39
     ভে
    0.38
     linha
    0.38
    ज्ञात
    0.37
     taşı
    0.37
    লেম
    0.37
     encontrar
    0.37
     нашли
    0.37
     meter
    0.36
    Activations Density 0.023%

    No Known Activations