© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43774
    Prev
    Next
    INDEX
    Explanations

    **zero tailpipe emissions**

    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_22_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
    MessageNow
    0.48
    вають
    0.41
    粥
    0.38
    ፃ
    0.37
    ásticos
    0.37
     eur
    0.36
     крупных
    0.36
    orgung
    0.36
    сування
    0.36
    istors
    0.35
    POSITIVE LOGITS
    இந்த
    0.42
     sabit
    0.41
     preventable
    0.40
     fijo
    0.40
     perdida
    0.40
    fixed
    0.40
     crea
    0.40
    chance
    0.39
    푝
    0.39
     permitido
    0.39
    Activations Density 0.000%

    No Known Activations