© 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. 7852
    Prev
    Next
    INDEX
    Explanations

    variable types

    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
    ுள்ளார்
    2.47
    oare
    2.01
    í
    2.00
    oretical
    1.98
    िया
    1.92
    \}$,
    1.91
     dinero
    1.86
     ishlab
    1.86
    ∨
    1.85
    ርት
    1.84
    POSITIVE LOGITS
    هم
    2.18
    म
    2.11
    মা
    2.05
     embarrass
    2.04
    好
    2.04
    Ǘ
    1.99
    መሳሳይ
    1.92
    ắc
    1.89
    ため
    1.88
    ный
    1.88
    Activations Density 0.005%

    No Known Activations