© 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. 7398
    Prev
    Next
    INDEX
    Explanations

    compt simult

    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
    ﺮ
    0.70
    ﻦ
    0.66
    ką
    0.59
    ﺤ
    0.59
    𝖽
    0.59
     adjournment
    0.58
    oint
    0.57
    ifient
    0.56
    bathy
    0.56
    ﻞ
    0.56
    POSITIVE LOGITS
     части
    0.47
     способ
    0.47
    關於
    0.46
     polymorphic
    0.45
     пев
    0.44
     اصول
    0.43
    ীতি
    0.43
    பெரும்
    0.43
    વ
    0.43
     Berechnung
    0.43
    Activations Density 0.001%

    No Known Activations