© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6594
    Prev
    Next
    INDEX
    Explanations

    a bit of a

    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
    いる
    2.34
    ্বর
    2.32
    ש
    2.24
    sand
    2.21
    룻
    2.14
     heps
    2.14
     kaikki
    2.12
    environ
    2.10
     creeps
    2.09
    mselves
    2.09
    POSITIVE LOGITS
    ية
    2.59
    й
    2.46
    y
    2.33
    ן
    2.28
    е
    2.26
    न
    2.21
    ни
    2.18
    ná
    2.11
    लिये
    2.10
    ε
    2.09
    Activations Density 0.033%

    No Known Activations