© 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-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141962
    Prev
    Next
    INDEX
    Explanations

    Dutch oven

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_width_262k_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
     dogged
    0.22
     frustrated
    0.18
     conséquent
    0.17
    ασίας
    0.17
     frustration
    0.17
     |”
    0.17
     peroneal
    0.17
     frustrating
    0.17
    њ
    0.16
     торговли
    0.16
    POSITIVE LOGITS
    Birds
    0.19
    Wifi
    0.18
    Bingo
    0.18
    Thailand
    0.18
    Photos
    0.18
    Ana
    0.18
    Ass
    0.18
    Halloween
    0.18
    Musik
    0.18
    UUID
    0.18
    Activations Density 0.000%

    No Known Activations