© 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. 3207
    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
    v
    1.27
    هم
    1.11
     Paddy
    1.11
    zuf
    1.11
     letzt
    1.09
    z
    1.07
     przed
    1.07
    𝑡
    1.06
     возможность
    1.04
    徒
    1.01
    POSITIVE LOGITS
    もちろん
    1.01
    Millions
    0.99
    juč
    0.99
    dyž
    0.97
    lasse
    0.97
    FileOutputStream
    0.97
     tales
    0.96
     tipped
    0.96
    Nasdaq
    0.95
    帼
    0.95
    Activations Density 0.037%

    No Known Activations