© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16814
    Prev
    Next
    INDEX
    Explanations

    code delimiters and keywords

    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_15_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
    烃
    0.28
    Nigeria
    0.28
     शाय
    0.27
     neutrals
    0.26
     κά
    0.26
    ہے
    0.26
     зону
    0.26
     الحلقة
    0.26
     subarrays
    0.26
    ”（
    0.25
    POSITIVE LOGITS
     :
    0.30
    ::
    0.28
     one
    0.26
    ():
    0.26
    *:
    0.26
     Suicide
    0.26
     Vien
    0.26
    .:
    0.26
    pm
    0.26
     March
    0.26
    Activations Density 0.039%

    No Known Activations