© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53155
    Prev
    Next
    INDEX
    Explanations

    data parsing or iteration

    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_30_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
    indows
    0.38
    投稿
    0.37
    Monty
    0.37
    キシ
    0.36
     활용
    0.36
    缶
    0.36
     यात्री
    0.35
     сервис
    0.35
    未必
    0.34
     영상
    0.34
    POSITIVE LOGITS
     Include
    0.45
    Include
    0.37
     penthouse
    0.36
    টল
    0.35
     nws
    0.35
    Includes
    0.34
    דם
    0.34
    讹
    0.34
     getContentPane
    0.34
     vesting
    0.34
    Activations Density 0.004%

    No Known Activations