© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56731
    Prev
    Next
    INDEX
    Explanations

    beforehand

    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_11_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
    م
    0.66
    ä
    0.63
     hä
    0.63
     morreu
    0.62
     бир
    0.62
    ாவில்
    0.61
    жде
    0.61
    ید
    0.59
     indique
    0.59
     blijven
    0.59
    POSITIVE LOGITS
    .
    0.69
    )
    0.62
    ;
    0.62
    [&
    0.61
     Crank
    0.59
    )”.
    0.57
    iami
    0.56
    ]
    0.56
    vana
    0.55
    Deer
    0.55
    Activations Density 0.000%

    No Known Activations