© 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-262K
    7. 11039
    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_262k_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
    ｙ
    0.80
     dentées
    0.79
     sbParams
    0.79
     offsetY
    0.79
    сійскай
    0.77
     zásobníku
    0.75
    ｃ
    0.73
    рит
    0.71
    指令
    0.71
    スティ
    0.71
    POSITIVE LOGITS
     (
    0.89
     =
    0.79
     IN
    0.76
     w
    0.74
     tragedy
    0.73
     New
    0.73
     char
    0.72
     film
    0.71
     BE
    0.71
    :
    0.71
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.