© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35788
    Prev
    Next
    INDEX
    Explanations

    list/vector manipulation

    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
     quantidade
    0.34
     किती
    0.34
    螨
    0.31
    quota
    0.30
    количество
    0.30
     कितनी
    0.29
    最小
    0.29
     পরিমাণ
    0.29
    arrive
    0.29
     prilikom
    0.29
    POSITIVE LOGITS
     mMediaPlayer
    0.33
     ମ
    0.33
     undis
    0.32
    ρεί
    0.30
     드리
    0.30
    Ě
    0.29
    琹
    0.29
     obeying
    0.29
     пред
    0.29
    ルフ
    0.29
    Activations Density 0.007%

    No Known Activations