© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43466
    Prev
    Next
    INDEX
    Explanations

    paddle tennis

    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_13_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
    }$;
    0.11
     Schule
    0.10
     misty
    0.10
     Ig
    0.10
     არ
    0.10
    )?;
    0.09
    さない
    0.09
     Kamu
    0.09
     عليه
    0.09
     ურთიერთ
    0.09
    POSITIVE LOGITS
     thalassemia
    0.11
    ç
    0.11
    נק
    0.11
    Ç
    0.10
     comorbidities
    0.10
     Timestamp
    0.10
    timestamp
    0.10
     downstream
    0.10
    Timestamp
    0.10
     dataGridView
    0.10
    Activations Density 0.002%

    No Known Activations