© 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. 8379
    Prev
    Next
    INDEX
    Explanations

    girlfriends

    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
    
    1.64
    $).
    1.49
     presenti
    1.47
    maximizing
    1.41
    multline
    1.36
    ные
    1.36
    м
    1.35
    mere
    1.31
    ترل
    1.30
    mim
    1.30
    POSITIVE LOGITS
    y
    1.68
    ו
    1.61
     fråga
    1.48
    artment
    1.48
    o
    1.47
    ও
    1.41
     ओर
    1.40
    ことは
    1.39
    з
    1.39
    ઈ
    1.38
    Activations Density 0.000%

    No Known Activations