© 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. 7090
    Prev
    Next
    INDEX
    Explanations

    challenging assumptions, power, gender

    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
    िक
    3.24
     conceivably
    2.90
    ното
    2.83
    fontSize
    2.76
    panic
    2.75
     tarde
    2.66
    то
    2.59
    ⎝
    2.57
    nal
    2.57
     incompar
    2.56
    POSITIVE LOGITS
    𝗿
    3.39
    𝗮
    3.23
    𝗻
    3.21
    𝘀
    2.88
    𝘂
    2.87
    𝗹
    2.74
    𝘁
    2.70
    𝗴
    2.66
    生素
    2.65
    𝗱
    2.62
    Activations Density 0.026%

    No Known Activations