© 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. 8844
    Prev
    Next
    INDEX
    Explanations

    Towards Data Science

    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
     Před
    1.36
     dever
    1.35
    ा
    1.34
    此
    1.33
    কার
    1.29
    και
    1.27
    मुखी
    1.26
    ी
    1.24
    鷗
    1.22
    不斷
    1.22
    POSITIVE LOGITS
    ية
    1.46
    }$&
    1.45
     gunpowder
    1.44
     concentric
    1.43
    اتها
    1.42
    ታት
    1.41
    चंद्र
    1.41
    🄰
    1.41
    bouw
    1.40
    ьте
    1.39
    Activations Density 0.000%

    No Known Activations