© 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. 2444
    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
    ு
    1.91
    ूव
    1.59
    folk
    1.55
     steers
    1.45
    comes
    1.42
     hundred
    1.40
     mów
    1.38
    ுமி
    1.37
     灬
    1.36
    jų
    1.36
    POSITIVE LOGITS
    ামুটি
    1.88
    er
    1.74
    quierda
    1.70
    න්
    1.63
     previsto
    1.63
     spelt
    1.62
    '/
    1.56
     FirebaseAuth
    1.54
     дворе
    1.51
    ل
    1.50
    Activations Density 0.002%

    No Known Activations