© 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. 7276
    Prev
    Next
    INDEX
    Explanations

    Jay-Z, Lopez, Street, walk

    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
    ح
    2.86
    ی
    2.85
    ैक
    2.75
    𝘪
    2.69
    𝘬
    2.68
    oa
    2.64
     triage
    2.53
    ک
    2.52
    𝘰
    2.50
    iteta
    2.47
    POSITIVE LOGITS
    nt
    2.61
    enti
    2.59
    ून
    2.57
    мон
    2.41
    lık
    2.35
     urm
    2.32
    Improve
    2.28
    ll
    2.27
    fillText
    2.26
    abot
    2.23
    Activations Density 0.000%

    No Known Activations