© 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. 156667
    Prev
    Next
    INDEX
    Explanations

    understanding use cases

    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
    on
    1.59
    :
    1.59
    ä
    1.43
    ill
    1.27
    ing
    1.23
    3
    1.23
    2
    1.22
    im
    1.20
    ind
    1.15
    ical
    1.13
    POSITIVE LOGITS
    ম
    1.48
    ק
    1.45
    와의
    1.31
     Š
    1.30
     Į
    1.28
    м
    1.28
     Ş
    1.20
     Ə
    1.17
    م
    1.17
    ટ
    1.16
    Activations Density 0.002%

    No Known Activations