© 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. 211621
    Prev
    Next
    INDEX
    Explanations

    International Union/Organization

    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
    水素
    0.46
     subspaces
    0.46
     سهله
    0.46
    MUX
    0.43
    闺
    0.43
    ניים
    0.43
     pembahasan
    0.43
    স্বাস্থ্য
    0.43
    ﻱ
    0.42
    Lifestyle
    0.41
    POSITIVE LOGITS
     Copyright
    0.48
    घो
    0.47
     कोण
    0.46
     Qatar
    0.44
     Across
    0.43
     Euro
    0.42
     Adjacent
    0.42
     As
    0.42
     Overall
    0.42
     Abroad
    0.42
    Activations Density 0.001%

    No Known Activations