© 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. 111679
    Prev
    Next
    INDEX
    Explanations

    Hz

    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
     by
    1.58
     봤
    1.20
    डी
    1.16
    ור
    1.11
     segu
    1.08
    );
    1.05
    all
    1.05
    el
    1.02
     distribu
    1.02
     esegu
    1.02
    POSITIVE LOGITS
    는
    1.22
     is
    1.16
    s
    1.16
    ll
    1.15
    á
    1.14
    ع
    1.09
    지
    1.06
    1.05
    ف
    1.01
    ۔
    1.00
    Activations Density 0.010%

    No Known Activations