© 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. 141274
    Prev
    Next
    INDEX
    Explanations

    Coco, Darwin, life

    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
     Assemble
    0.51
    瘾
    0.50
    sø
    0.49
    För
    0.49
    dü
    0.49
     Assembl
    0.48
     Allo
    0.48
     Ment
    0.47
     اسمبلی
    0.47
    affection
    0.47
    POSITIVE LOGITS
    ين
    0.55
    X
    0.49
    ルド
    0.48
     individuos
    0.48
     llrp
    0.48
     neural
    0.47
     de
    0.47
     anomalous
    0.46
     que
    0.46
     بواسطة
    0.46
    Activations Density 0.000%

    No Known Activations