© 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. 87351
    Prev
    Next
    INDEX
    Explanations

    parsing html with BeautifulSoup

    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
     şeyler
    0.52
    娠
    0.49
     новое
    0.49
    что
    0.47
     ổ
    0.46
     IDC
    0.46
     beginnt
    0.46
    сле
    0.46
    ж
    0.45
    шь
    0.45
    POSITIVE LOGITS
     grueling
    0.55
     تكعيب
    0.46
     극
    0.43
    iona
    0.42
     vehement
    0.42
     suggestion
    0.41
    ruction
    0.40
     sculptural
    0.40
    Suggestion
    0.40
    atik
    0.39
    Activations Density 0.010%

    No Known Activations