© 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. 7396
    Prev
    Next
    INDEX
    Explanations

    configure terminal

    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
    এক
    1.54
     eigens
    1.29
    setInt
    1.27
     posX
    1.23
     immobilization
    1.23
    pias
    1.23
    ں
    1.22
    watts
    1.20
     amplitude
    1.20
     immobilized
    1.19
    POSITIVE LOGITS
    ה
    1.86
    ת
    1.64
    া
    1.56
    er
    1.45
    л
    1.40
    a
    1.40
    erste
    1.31
    erode
    1.31
    konto
    1.30
    המ
    1.27
    Activations Density 0.000%

    No Known Activations