© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20166
    Prev
    Next
    INDEX
    Explanations

    Form

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    ைய
    0.34
    வியை
    0.34
    chond
    0.33
    ச்சியை
    0.31
     அக
    0.30
     established
    0.30
    ्ज
    0.30
    }]}\
    0.30
    드를
    0.30
    два
    0.30
    POSITIVE LOGITS
     Form
    2.27
    Form
    2.23
     FORM
    1.90
     फॉर्म
    1.89
    form
    1.88
     form
    1.83
    FORM
    1.80
    フォーム
    1.77
     فرم
    1.74
     ফর্ম
    1.73
    Activations Density 0.065%

    No Known Activations