© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45388
    Prev
    Next
    INDEX
    Explanations

    programming keywords and code structure

    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_22_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
    ak
    0.49
    </b>
    0.46
    oul
    0.44
    ace
    0.39
    eneuve
    0.38
    oufl
    0.38
    ib
    0.38
    ui
    0.37
     >>
    0.37
     and
    0.37
    POSITIVE LOGITS
     orthogonal
    0.49
    orthogonal
    0.47
     oposición
    0.46
    oppositions
    0.43
    స్తాయి
    0.43
    восто
    0.42
    Opposition
    0.41
    рье
    0.40
     égales
    0.40
     있어야
    0.40
    Activations Density 0.007%

    No Known Activations