© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199027
    Prev
    Next
    INDEX
    Explanations

    classical Latin

    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_15_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
     वाइज
    0.59
    aarr
    0.58
     ตาม
    0.57
     можа
    0.57
    !</
    0.57
     хотим
    0.56
     打开
    0.56
    than
    0.55
    μου
    0.55
     不同
    0.55
    POSITIVE LOGITS
    IP
    0.58
    IN
    0.57
    IC
    0.55
    Money
    0.53
    BLOCK
    0.52
    TO
    0.52
    he
    0.51
    v
    0.50
    *}
    0.50
    Heart
    0.49
    Activations Density 0.002%

    No Known Activations