© 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. 8110
    Prev
    Next
    INDEX
    Explanations

    k-pop, kdrama, korean

    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
    на
    2.34
    ্ব
    2.01
    
    1.90
    ان
    1.85
    க்களை
    1.84
    я
    1.81
    ை
    1.80
    ot
    1.78
    க்கள்
    1.72
    ار
    1.71
    POSITIVE LOGITS
    proving
    1.99
    それでは
    1.92
     では
    1.90
     mortg
    1.86
     appeals
    1.86
    राम
    1.85
     straining
    1.83
     reassuring
    1.82
    ucle
    1.81
    ⎥
    1.80
    Activations Density 0.026%

    No Known Activations