© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33319
    Prev
    Next
    INDEX
    Explanations

    hook

    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_31_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
    굴
    0.38
     nahil
    0.36
     depot
    0.35
    Sharma
    0.35
    Jim
    0.35
    ッテ
    0.35
    Channel
    0.35
     சேன
    0.35
    𝑏
    0.34
    MAF
    0.34
    POSITIVE LOGITS
    Hook
    0.64
     Hook
    0.62
     hook
    0.61
    hook
    0.58
     hooks
    0.57
     hooked
    0.53
     Hooks
    0.52
     hooking
    0.52
    Hooks
    0.51
    鉤
    0.50
    Activations Density 0.002%

    No Known Activations