© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88111
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
    žeme
    0.41
    cal
    0.41
    Ꭶ
    0.40
     بالق
    0.39
    mesinin
    0.39
    Ult
    0.38
    Seeing
    0.37
    ÉT
    0.37
    OrCallback
    0.37
    ?]
    0.36
    POSITIVE LOGITS
     coincides
    0.52
     impulses
    0.51
     adolescentes
    0.51
    yards
    0.50
    یه
    0.47
    لیت
    0.47
     inconsc
    0.46
    stun
    0.46
     حتی
    0.46
    ایط
    0.46
    Activations Density 0.000%

    No Known Activations