© 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. 8566
    Prev
    Next
    INDEX
    Explanations

    callouts or writing

    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
    ल
    1.93
    TING
    1.80
    RE
    1.62
    𝘺
    1.58
    𝘭
    1.57
     fait
    1.56
    т
    1.52
     koje
    1.52
     hecho
    1.52
    Bounded
    1.52
    POSITIVE LOGITS
    णिज्य
    1.69
     supple
    1.41
    lgende
    1.39
    ඍ
    1.35
     cercano
    1.34
    犸
    1.34
     _,
    1.31
     বয়সী
    1.31
    ган
    1.29
    im
    1.27
    Activations Density 0.004%

    No Known Activations