© 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. 6412
    Prev
    Next
    INDEX
    Explanations

    Not worth it

    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
    ка
    3.49
    ु
    3.44
    ки
    2.80
    码
    2.77
    ITY
    2.74
    ity
    2.64
    на
    2.58
    ع
    2.55
    री
    2.53
    
    2.49
    POSITIVE LOGITS
    ه
    3.33
    ein
    3.16
    ğı
    2.88
    𝘁
    2.87
    o
    2.84
    años
    2.81
    ਨ
    2.73
    aar
    2.66
     automorphisms
    2.64
     been
    2.60
    Activations Density 0.226%

    No Known Activations