© 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. 195155
    Prev
    Next
    INDEX
    Explanations

    blend modes and light

    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
    襷
    0.54
    σε
    0.51
     т
    0.51
    )",
    0.49
     t
    0.46
     टाक
    0.46
     Krom
    0.46
    स
    0.46
    ギフト
    0.45
     ")
    0.45
    POSITIVE LOGITS
    žia
    0.60
    atians
    0.51
    劳
    0.51
    rivel
    0.50
     ścian
    0.48
    irties
    0.48
    阌
    0.48
     remaster
    0.48
     nouveau
    0.47
     propylene
    0.47
    Activations Density 0.001%

    No Known Activations