© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143897
    Prev
    Next
    INDEX
    Explanations

    companion specification, app, animal, object, ads, website

    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_0_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
    oja
    1.05
    ι
    1.05
    ังก์
    1.04
    ти
    1.02
    h
    1.02
    สิ้น
    0.99
    onium
    0.97
    toLowerCase
    0.96
    ⏫
    0.95
    ações
    0.94
    POSITIVE LOGITS
    م
    1.90
    ك
    1.83
    м
    1.57
    й
    1.52
    ل
    1.46
    ER
    1.41
    كَ
    1.41
    ES
    1.35
     что
    1.35
    لر
    1.33
    Activations Density 0.001%

    No Known Activations