© 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. 158196
    Prev
    Next
    INDEX
    Explanations

    credit, debit, dates

    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
    ب
    1.27
     demikian
    1.12
     and
    1.08
    น
    1.07
    บ
    1.02
     to
    1.00
    মি
    1.00
    آ
    0.99
     It
    0.99
    n
    0.98
    POSITIVE LOGITS
    '
    1.70
    _
    1.64
    {
    1.59
    //
    1.41
    {//
    1.34
    $('#
    1.21
    aría
    1.13
    +
    1.12
    '+
    1.10
    2
    1.09
    Activations Density 0.000%

    No Known Activations