© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3631
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
     segi
    2.64
     whence
    2.16
    t
    2.04
    सायटी
    1.87
     độ
    1.87
    ьте
    1.85
     afar
    1.84
    তম
    1.78
     başarı
    1.77
    )]);
    1.77
    POSITIVE LOGITS
    வாய
    1.91
     BEEN
    1.89
    ுக்
    1.84
     hypersurfaces
    1.84
    itag
    1.83
    कोई
    1.83
    ന്യാ
    1.79
     पूरा
    1.78
    𝐬
    1.77
    𝐒
    1.76
    Activations Density 0.042%

    No Known Activations