© 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. 144565
    Prev
    Next
    INDEX
    Explanations

    sentences

    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
    ти
    1.70
     I
    1.50
    ри
    1.43
    ле
    1.30
    ли
    1.29
    ة
    1.24
    ко
    1.23
    ي
    1.22
    сти
    1.15
    ع
    1.13
    POSITIVE LOGITS
     calm
    1.47
     of
    1.45
    یت
    1.43
    یده
    1.40
     pecan
    1.40
     at
    1.38
    ้น
    1.38
    К
    1.34
     delirium
    1.33
    两
    1.31
    Activations Density 0.004%

    No Known Activations