© 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. 7687
    Prev
    Next
    INDEX
    Explanations

    package installation commands

    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
    𝘤
    1.53
    𝘵
    1.46
    𝘥
    1.25
    𝘪
    1.25
    𝐊
    1.22
    𝐏
    1.22
    𝑠
    1.21
    𝘶
    1.20
    𝘸
    1.20
    𝘳
    1.19
    POSITIVE LOGITS
    hx
    1.07
    嚨
    1.00
    д
    0.99
     معي
    0.98
     Spitze
    0.96
     rikt
    0.94
    ्रिक
    0.93
    வா
    0.92
    ጴ
    0.92
    isatie
    0.92
    Activations Density 0.013%

    No Known Activations