© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7817
    Prev
    Next
    INDEX
    Explanations

    Miami-Dade County

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
     columnIndex
    0.75
    খান
    0.72
    umma
    0.70
     Burj
    0.68
    ꜱ
    0.68
    جه
    0.67
    ১
    0.66
    ال
    0.65
    ᴛ
    0.65
    ра
    0.64
    POSITIVE LOGITS
     eben
    0.74
    ि
    0.73
     stepwise
    0.70
     gesamte
    0.68
    حضرت
    0.66
     gesam
    0.66
    лькі
    0.65
    ine
    0.65
    リー
    0.64
    ﻡ
    0.63
    Activations Density 0.002%

    No Known Activations