© 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. 8605
    Prev
    Next
    INDEX
    Explanations

    Crete or Brexit

    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
    ्च
    2.74
    রুখ
    2.64
    rupted
    2.63
    ]::-
    2.62
    य
    2.59
    в
    2.55
    𝗘
    2.49
    hā
    2.49
    }$\
    2.46
     المتحدة
    2.45
    POSITIVE LOGITS
    शील
    3.11
    
    2.49
     épaisse
    2.42
     ehemal
    2.42
     fueran
    2.41
    وان
    2.38
     ограничењима
    2.36
    nard
    2.36
    要是
    2.31
     iç
    2.31
    Activations Density 0.014%

    No Known Activations