© 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. 3244
    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
     moot
    2.67
     scared
    2.54
    vä
    2.49
    ლ
    2.45
    le
    2.44
    н
    2.44
    لل
    2.33
    سری
    2.31
     ami
    2.30
     headway
    2.27
    POSITIVE LOGITS
    EN
    2.63
    en
    2.60
    ن
    2.44
    cok
    2.30
     tidur
    2.29
    ~/
    2.22
    できる
    2.18
     mistakes
    2.17
     forc
    2.17
    𝒆
    2.16
    Activations Density 0.028%

    No Known Activations