© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124319
    Prev
    Next
    INDEX
    Explanations

    names and specific terms

    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_3_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
    '
    0.86
    i
    0.82
    a
    0.77
    י
    0.77
    NA
    0.73
    BA
    0.69
    BC
    0.68
    e
    0.68
    ازی
    0.67
    המ
    0.66
    POSITIVE LOGITS
    (
    0.64
    か
    0.58
    ៤
    0.54
    ый
    0.54
    4
    0.53
    ៦
    0.53
    ២
    0.52
    ций
    0.51
    cepteur
    0.49
     quell
    0.49
    Activations Density 0.002%

    No Known Activations