© 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. 6312
    Prev
    Next
    INDEX
    Explanations

    json keys

    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
    en
    2.89
    ことが
    2.71
    psons
    2.60
    ડા
    2.53
    ड़ा
    2.44
    в
    2.44
    ი
    2.42
    एल
    2.37
    y
    2.35
    िक
    2.35
    POSITIVE LOGITS
     таки
    3.16
    ential
    2.92
     ​​
    2.83
    ل
    2.67
     foi
    2.64
     ​​​​
    2.60
     hran
    2.58
    fare
    2.55
    Thông
    2.53
    萋
    2.52
    Activations Density 0.021%

    No Known Activations