© 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. 7554
    Prev
    Next
    INDEX
    Explanations

    java.net

    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
    ्या
    2.51
    রা
    2.45
    iring
    2.41
    ے
    2.38
    
    2.38
    ು
    2.35
    ும்போது
    2.29
    ی
    2.18
    cribed
    2.17
    ся
    2.16
    POSITIVE LOGITS
    න්
    2.83
     raindrops
    2.76
    Diese
    2.73
    یثیت
    2.66
     emboss
    2.55
    ~/
    2.51
     erre
    2.50
    缺陷
    2.36
    بق
    2.32
     embossing
    2.32
    Activations Density 0.001%

    No Known Activations