© 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. 2576
    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
    ра
    1.21
    𝐠
    1.10
    ल
    1.10
     envió
    1.08
     cusp
    1.06
     skulle
    1.06
    お
    1.00
     když
    1.00
     hacía
    0.99
    𝖾
    0.99
    POSITIVE LOGITS
    en
    1.03
    다면
    1.00
    под
    0.97
    }{|\
    0.97
    OLINA
    0.95
    ли
    0.95
     же
    0.95
    ->"
    0.94
    丿
    0.93
    letzt
    0.92
    Activations Density 0.003%

    No Known Activations