© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 224329
    Prev
    Next
    INDEX
    Explanations

    new [noun]

    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_10_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
    _
    0.54
     epistle
    0.41
     as
    0.40
     کە
    0.40
     bahawa
    0.39
     chrysanthemum
    0.37
    ião
    0.37
     posti
    0.37
    urra
    0.36
     array
    0.35
    POSITIVE LOGITS
    ائف
    0.48
     wszel
    0.48
    В
    0.48
    na
    0.47
    Ва
    0.46
    От
    0.45
    На
    0.43
    Д
    0.42
    да
    0.41
    ну
    0.41
    Activations Density 0.007%

    No Known Activations