© 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. 8529
    Prev
    Next
    INDEX
    Explanations

    directional information, south

    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
    ്രീ
    1.50
     amply
    1.46
     immunoblot
    1.46
    bhp
    1.39
    ক
    1.37
     Admittedly
    1.36
    ค์
    1.30
     accomplishments
    1.30
     glitches
    1.29
     forfeit
    1.27
    POSITIVE LOGITS
    Одна
    1.48
    ￣
    1.32
    wark
    1.22
    textcolor
    1.20
    му
    1.19
    ◔
    1.19
    verde
    1.19
    pedido
    1.18
     cuadrada
    1.17
     Никола
    1.16
    Activations Density 0.017%

    No Known Activations