© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200623
    Prev
    Next
    INDEX
    Explanations

    fuel injectors

    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
    racellular
    0.56
    taker
    0.55
    tempor
    0.50
    Invest
    0.50
     intracellular
    0.48
    }$
    0.48
    invest
    0.47
    投資
    0.47
    vdash
    0.47
    rise
    0.47
    POSITIVE LOGITS
                             
    0.54
     ד
    0.54
     یکی
    0.54
     би
    0.53
    بل
    0.52
     patrols
    0.52
     بن
    0.52
     л
    0.52
     бил
    0.50
     ሚ
    0.50
    Activations Density 0.001%

    No Known Activations