© 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. 6980
    Prev
    Next
    INDEX
    Explanations

    makes use of

    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
    போன்ற
    1.59
     elett
    1.57
    tert
    1.45
     perceber
    1.41
    ние
    1.40
    तील
    1.40
    ם
    1.40
    չ
    1.37
    𝘮
    1.34
     tecnica
    1.34
    POSITIVE LOGITS
    an
    1.88
    or
    1.73
    द
    1.63
    ł
    1.63
     illustrious
    1.61
    at
    1.60
    گیری
    1.56
     poč
    1.51
    a
    1.50
     hỏi
    1.49
    Activations Density 0.005%

    No Known Activations