© 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. 8626
    Prev
    Next
    INDEX
    Explanations

    The Weight of

    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
     Dafür
    2.83
    
    2.48
     kunna
    2.35
    }$,
    2.34
     
    2.33
     thence
    2.33
    }$.
    2.30
     tvor
    2.29
    ㅑ
    2.27
     জনের
    2.25
    POSITIVE LOGITS
    ر
    2.33
    lifting
    2.15
    বসাই
    2.12
    บาล
    2.07
     lượng
    2.04
     scant
    2.04
    _{*
    2.02
    нок
    2.00
    णिज्य
    1.98
    वत्ता
    1.97
    Activations Density 0.070%

    No Known Activations