© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208732
    Prev
    Next
    INDEX
    Explanations

    non-Latin characters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    했을
    0.40
     ?>"
    0.38
    <td>
    0.37
    (["
    0.37
    词
    0.37
    ('',
    0.37
    ('/',
    0.36
    yser
    0.36
     fiction
    0.36
    forderung
    0.36
    POSITIVE LOGITS
    ক্
    0.40
     arraigned
    0.39
     சார்ப
    0.38
     स्क्रीनिंग
    0.37
    ].)
    0.37
    spell
    0.36
    peria
    0.36
    пот
    0.36
     instigated
    0.36
    Spell
    0.35
    Activations Density 0.001%

    No Known Activations