© 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. 8822
    Prev
    Next
    INDEX
    Explanations

    Thatcher, trade, Thar Desert

    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
    ت
    2.81
    𝑔
    2.78
    ℎ
    2.78
    𝑒
    2.72
    𝑎
    2.66
    та
    2.65
    𝑜
    2.63
    ট
    2.56
    ر
    2.55
    దు
    2.45
    POSITIVE LOGITS
    هایی
    2.99
     ferv
    2.90
    েন
    2.76
    amine
    2.61
     participle
    2.55
     fecha
    2.54
    ków
    2.51
    うえ
    2.44
    Interfaz
    2.43
     término
    2.40
    Activations Density 0.000%

    No Known Activations