© 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. 158997
    Prev
    Next
    INDEX
    Explanations

    weight unit kg

    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
    ר
    2.00
    ad
    1.62
    ี
    1.58
    is
    1.46
    et
    1.42
    il
    1.42
    ни
    1.36
    ти
    1.33
    ర్
    1.28
    y
    1.23
    POSITIVE LOGITS
     of
    1.54
     are
    1.34
    ९
    1.12
    yla
    1.05
    OF
    1.02
     jonka
    1.00
    ney
    0.99
    {
    0.96
    $
    0.96
    ৩
    0.94
    Activations Density 0.002%

    No Known Activations