© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 207528
    Prev
    Next
    INDEX
    Explanations

    keywords, expressions, integrated

    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_25_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
     %%
    0.40
    ：（
    0.39
     judged
    0.38
    стами
    0.37
    %%
    0.37
     יי
    0.37
    후
    0.36
     одно
    0.36
     vanishes
    0.35
     извест
    0.35
    POSITIVE LOGITS
     intégr
    0.46
    保育
    0.45
     एकीकृत
    0.45
    න
    0.43
    imir
    0.42
     intégré
    0.40
    abhar
    0.39
     kini
    0.39
     integrado
    0.38
    चिक
    0.38
    Activations Density 0.000%

    No Known Activations