© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4640
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_16k_l0_medium
    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
    c
    0.71
    De
    0.69
    model
    0.68
    ה
    0.68
    im
    0.67
    in
    0.65
    ﺪ
    0.64
    API
    0.64
    Beim
    0.64
    高
    0.63
    POSITIVE LOGITS
     condivid
    0.75
     arrears
    0.72
     hopes
    0.71
     وفي
    0.71
     pergunt
    0.70
     sectors
    0.69
     Saclay
    0.68
     negeri
    0.68
    সিসি
    0.68
     городах
    0.67
    Activations Density 0.000%

    No Known Activations