© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6500
    Prev
    Next
    INDEX
    Explanations

    gold standard

    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
    특별시
    2.32
    म
    2.26
    mining
    2.24
     shoving
    2.11
     claws
    2.11
    и
    2.06
    Zeneca
    2.05
    teaser
    2.03
    feather
    2.01
    <unused302>
    2.00
    POSITIVE LOGITS
    ні
    2.25
    ن
    2.20
     aikana
    2.18
     bila
    2.13
    გ
    2.12
     prennent
    2.10
     ouvertes
    2.09
    دت
    2.08
    ➩
    2.06
     dirigés
    2.04
    Activations Density 0.001%

    No Known Activations