© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211345
    Prev
    Next
    INDEX
    Explanations

    solve this

    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
    ?’
    0.46
    ?”
    0.43
     Happen
    0.42
    friger
    0.41
     geschaffen
    0.41
    ʖ
    0.41
    য়াল
    0.41
    ᾳ
    0.41
    forma
    0.40
     કંઈ
    0.40
    POSITIVE LOGITS
     সোমবার
    0.46
     jednej
    0.45
     종료
    0.44
     Leonard
    0.44
     सोमवार
    0.43
     petrol
    0.43
     cream
    0.43
     אחת
    0.42
     очереди
    0.42
    が高い
    0.42
    Activations Density 0.002%

    No Known Activations