© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209719
    Prev
    Next
    INDEX
    Explanations

    software bundle/library/gem

    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_20_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
    GTBase
    0.48
     શું
    0.44
    %);
    0.43
     />);
    0.43
     спро
    0.42
     Bloomfield
    0.41
    )';
    0.40
     ком
    0.40
     Pandora
    0.40
    ጅም
    0.40
    POSITIVE LOGITS
    ankind
    0.48
    ле
    0.46
    ི
    0.44
    ո
    0.43
    encias
    0.42
    ék
    0.40
    lica
    0.40
    rı
    0.40
    lic
    0.38
    onimo
    0.38
    Activations Density 0.000%

    No Known Activations