© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106851
    Prev
    Next
    INDEX
    Explanations

    "ie" followed by specific words

    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_1_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
    das
    1.33
    don
    1.23
    dal
    1.18
    daten
    1.16
    '
    1.16
    dog
    1.12
    dle
    1.09
    ders
    1.09
    ों
    1.07
    lamp
    1.05
    POSITIVE LOGITS
    ری
    1.48
    ர
    1.48
    ب
    1.30
    ");
    1.17
    p
    1.17
    را
    1.16
    ו
    1.16
    ט
    1.15
     ۶
    1.11
    リ
    1.11
    Activations Density 0.000%

    No Known Activations