© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157486
    Prev
    Next
    INDEX
    Explanations

    annual / annualized / rates / -ize / -ise / -ize

    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
    to
    1.91
    with
    1.62
    that
    1.59
    sp
    1.56
    2
    1.55
    time
    1.38
    1.31
    i
    1.31
    no
    1.29
    string
    1.29
    POSITIVE LOGITS
    ியின்
    1.63
    ৯
    1.25
     in
    1.22
    ก
    1.22
    ות
    1.14
    ியும்
    1.09
    {
    1.09
     a
    1.06
    ᱕
    1.06
    owego
    1.05
    Activations Density 0.000%

    No Known Activations