© 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. 8216
    Prev
    Next
    INDEX
    Explanations

    UI component tags

    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
    д
    2.65
    y
    2.43
    iendo
    2.38
     पीना
    2.32
    یه
    2.27
    ‫
    2.25
    нда
    2.24
    b
    2.17
    িক
    2.16
    ността
    2.14
    POSITIVE LOGITS
    勮
    2.49
     strides
    2.35
    勬
    2.31
    YD
    2.16
     slow
    2.14
     cytochrome
    2.14
     CBR
    2.13
     Tämä
    2.11
    grado
    2.10
     fille
    2.07
    Activations Density 0.030%

    No Known Activations