© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8384
    Prev
    Next
    INDEX
    Explanations

    game engine Godot

    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_40_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
     केवळ
    0.46
     опу
    0.39
    箅
    0.38
     Анна
    0.37
    住了
    0.37
     Cantonese
    0.37
     gave
    0.37
    Dave
    0.36
    Insp
    0.36
    าลัย
    0.36
    POSITIVE LOGITS
     гли
    0.41
    神的
    0.39
    จทย์
    0.36
     gly
    0.36
    ."]
    0.36
    レンチ
    0.36
    glEnd
    0.35
     मक्
    0.35
    gp
    0.35
    神
    0.34
    Activations Density 0.022%

    No Known Activations