© 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. 160373
    Prev
    Next
    INDEX
    Explanations

    Wien, Wiener, Wieder

    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
    3
    1.54
    5
    1.43
    ために
    1.34
    6
    1.34
    ون
    1.20
     variés
    1.13
    9
    1.12
     empêcher
    1.09
    4
    1.09
    ן
    1.07
    POSITIVE LOGITS
    '
    2.45
     It
    1.78
    y
    1.41
     I
    1.32
    h
    1.23
    1.20
    to
    1.20
     These
    1.17
     This
    1.16
    g
    1.16
    Activations Density 0.000%

    No Known Activations