© 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. 7605
    Prev
    Next
    INDEX
    Explanations

    Brazil, capybara, Ipanema

    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
    ์
    3.58
    ма
    3.45
    ه
    3.08
    ittings
    2.70
     forcefully
    2.64
    ziger
    2.59
     disobey
    2.52
     sclerosis
    2.51
    ሳሪያ
    2.51
    aqu
    2.50
    POSITIVE LOGITS
    zinho
    2.49
    о
    2.46
     éd
    2.36
     imm
    2.34
     corpor
    2.32
    А
    2.30
     וכ
    2.24
     agricole
    2.23
    $;
    2.18
     acum
    2.18
    Activations Density 0.006%

    No Known Activations