© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 89394
    Prev
    Next
    INDEX
    Explanations

    perl `class` or python `window`

    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_18_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
    :
    0.53
     peaceful
    0.47
     peacefully
    0.45
    ya
    0.44
     desde
    0.44
    ve
    0.42
    clusive
    0.42
     caves
    0.42
    *
    0.41
     geological
    0.40
    POSITIVE LOGITS
    둴
    0.54
     haupt
    0.49
     niektó
    0.47
     homozyg
    0.47
    뉸
    0.46
    mité
    0.46
     wyjątk
    0.45
     উঠবে
    0.45
     některé
    0.45
     będzie
    0.44
    Activations Density 0.001%

    No Known Activations