© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261690
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation

    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_22_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
     diligently
    0.14
     defibr
    0.13
    োজ
    0.13
    ਊ
    0.13
    dg
    0.13
     scre
    0.13
     compromised
    0.13
    bevel
    0.13
     essential
    0.13
    ন্ত্রণ
    0.13
    POSITIVE LOGITS
     名称
    0.15
     nếu
    0.15
     साठी
    0.15
     якщо
    0.15
    摫
    0.15
     если
    0.15
     इच्छा
    0.15
    如果你
    0.15
     त
    0.14
     समर्थ
    0.14
    Activations Density 0.000%

    No Known Activations