© 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. 57974
    Prev
    Next
    INDEX
    Explanations

    process of

    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
    {
    1.68
    .
    1.41
    y
    1.36
    ED
    1.17
    Date
    1.13
    ני
    1.13
    AR
    1.11
    It
    1.09
    v
    1.09
    September
    1.08
    POSITIVE LOGITS
    és
    1.34
    ли
    1.25
    ieurs
    1.23
    يك
    1.19
    其他
    1.13
    ́t
    1.13
     таки
    1.11
    ع
    1.10
    ován
    1.09
    ου
    1.06
    Activations Density 0.003%

    No Known Activations