© 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. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 1345
    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_12_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
    важа
    0.35
    igrant
    0.35
    endem
    0.34
    otrop
    0.32
    மல
    0.32
    agati
    0.31
    Ced
    0.31
    Ἄ
    0.30
    یند
    0.30
    έν
    0.30
    POSITIVE LOGITS
    openg
    0.38
     ولی
    0.37
     illetve
    0.37
     filly
    0.37
    ாலிக
    0.36
    朹
    0.35
    ひと
    0.35
     Tactical
    0.35
    drink
    0.35
     poro
    0.35
    Activations Density 0.012%

    No Known Activations