© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214079
    Prev
    Next
    INDEX
    Explanations

    professional/technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     dece
    0.45
     conflic
    0.40
     Animations
    0.38
    復
    0.38
     देखता
    0.38
     troubles
    0.38
     mas
    0.37
     ҷ
    0.37
    繁
    0.37
     Wealth
    0.37
    POSITIVE LOGITS
     строк
    0.43
     podataka
    0.42
     maxill
    0.42
     отношений
    0.41
     растений
    0.40
    sigma
    0.40
    গুলোর
    0.40
     собак
    0.39
    들의
    0.39
     στον
    0.39
    Activations Density 0.000%

    No Known Activations