© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175976
    Prev
    Next
    INDEX
    Explanations

    algorithm execution

    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_20_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
     escuchar
    0.42
     صوت
    0.41
    බ්
    0.41
    军
    0.40
    焯
    0.40
    เสียง
    0.40
    ﺔ
    0.40
    ("../
    0.39
    Continu
    0.39
    摖
    0.39
    POSITIVE LOGITS
     fetches
    0.48
    ണ്ടും
    0.42
    冷蔵
    0.42
    indrome
    0.41
     způso
    0.41
     specular
    0.41
     quests
    0.40
     spô
    0.40
     ontological
    0.40
    urov
    0.40
    Activations Density 0.001%

    No Known Activations