© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111344
    Prev
    Next
    INDEX
    Explanations

    das 'u', 'hes', 'her', 'Boot', 'ani'

    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_2_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
    س
    1.37
     esperado
    1.13
     empêcher
    1.13
    ップ
    1.12
     améliorer
    1.12
     energético
    1.04
    য়
    1.04
    ف
    1.04
     émissions
    1.03
    ty
    1.02
    POSITIVE LOGITS
    '
    1.74
    -
    1.48
    l
    1.45
    :
    1.40
    n
    1.38
    is
    1.16
    ↵
    1.13
    en
    1.11
    la
    1.08
    ۰
    1.05
    Activations Density 0.000%

    No Known Activations