© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165448
    Prev
    Next
    INDEX
    Explanations

    increment/click event

    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_31_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
    ultura
    0.36
    EXIT
    0.35
    intell
    0.35
    ﹣
    0.35
     গোষ্ঠী
    0.35
     겁니다
    0.34
    twenty
    0.34
     سوز
    0.34
    第四
    0.34
    lung
    0.34
    POSITIVE LOGITS
    duire
    0.36
     cheap
    0.36
     ups
    0.35
    ଳ
    0.35
     Moro
    0.34
    溉
    0.33
     naturally
    0.33
    пня
    0.32
     छव
    0.32
     slightly
    0.32
    Activations Density 0.002%

    No Known Activations