© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202221
    Prev
    Next
    INDEX
    Explanations

    TABLETABLE_NAMEtablebase

    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_6_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
    ה
    1.32
    ۲
    1.00
    ปี
    0.99
    غ
    0.98
    ۹
    0.97
     on
    0.96
    אל
    0.93
    תו
    0.91
    考え
    0.91
    ני
    0.89
    POSITIVE LOGITS
    ur
    1.35
    s
    1.26
    ่า
    1.17
    ik
    1.13
    '
    1.02
    س
    1.01
    ant
    0.98
    {
    0.98
    }*/
    0.97
     Ceremon
    0.96
    Activations Density 0.001%

    No Known Activations