© 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. 8479
    Prev
    Next
    INDEX
    Explanations

    merlin, mervyn, silas

    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
    ../../
    2.18
    enje
    2.12
    assertThat
    2.10
    儿
    2.08
    en
    2.05
    ../../../
    1.97
    ﻡ
    1.93
    眙
    1.90
     defies
    1.86
    inescent
    1.84
    POSITIVE LOGITS
    et
    2.08
    至於
    1.97
     चलकर
    1.96
    स
    1.96
    jde
    1.92
    ILLIPS
    1.91
    不
    1.88
    ри
    1.88
    IENTE
    1.87
     речь
    1.86
    Activations Density 0.003%

    No Known Activations