© 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. 8548
    Prev
    Next
    INDEX
    Explanations

    html/jsx structure and content

    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
    arası
    2.26
    on
    2.15
    er
    2.07
    ার
    2.02
    ᴄ
    2.02
    𝐓
    1.98
    𝚝
    1.97
    𝚃
    1.93
    𝚌
    1.92
    o
    1.90
    POSITIVE LOGITS
    ic
    2.49
    ی
    2.02
    ../../
    1.90
    枚
    1.85
    я
    1.76
    как
    1.76
     principios
    1.71
    ર્મ
    1.70
     primeiros
    1.68
    ke
    1.68
    Activations Density 0.029%

    No Known Activations