© 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. 172404
    Prev
    Next
    INDEX
    Explanations

    would like to express gratitude

    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
     downgraded
    0.47
     fatalities
    0.46
     obscures
    0.45
     Вікі
    0.45
    ゞ
    0.44
     erkennen
    0.43
     只
    0.42
     випадку
    0.42
     cancelling
    0.42
     diversi
    0.42
    POSITIVE LOGITS
     Bally
    0.46
     captain
    0.45
     manner
    0.44
     મહે
    0.41
     supervisor
    0.40
    卧
    0.40
     baut
    0.40
     જૂ
    0.40
    Supervisor
    0.40
    县
    0.40
    Activations Density 0.000%

    No Known Activations