© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 144821
    Prev
    Next
    INDEX
    Explanations

    bacon

    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
    2
    1.41
    ch
    1.32
    ли
    1.31
     categor
    1.30
    哪里
    1.16
    لي
    1.11
     is
    1.10
    that
    1.09
    อย่าง
    1.06
    שי
    1.03
    POSITIVE LOGITS
    et
    1.72
    ai
    1.66
    ت
    1.38
    x
    1.30
    də
    1.30
    ik
    1.27
    േ
    1.23
    and
    1.22
    ek
    1.20
    ாக
    1.20
    Activations Density 0.000%

    No Known Activations