© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44066
    Prev
    Next
    INDEX
    Explanations

    For example "Forvo", "YouTubers", "The Merge", "Canva"

    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_22_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
     recognisable
    0.34
    潙
    0.34
    ępnie
    0.32
    poon
    0.31
    Once
    0.31
     continuing
    0.31
     meagre
    0.31
    യില
    0.31
    Wei
    0.30
     raided
    0.30
    POSITIVE LOGITS
     convenc
    0.32
    름
    0.32
     kab
    0.29
     exif
    0.29
     cine
    0.29
     maqu
    0.29
     cerrar
    0.29
     cursos
    0.29
     音
    0.28
     allerg
    0.28
    Activations Density 0.013%

    No Known Activations