© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 749
    Prev
    Next
    INDEX
    Explanations

    HTML image tags and associated attributes like width, height, and URLs.

    oai_token-act-pair · gemini-2.0-flash

    Images and file extensions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.49
    charlie
    -0.45
    >(&
    -0.42
     Rom
    -0.42
    券
    -0.41
    Estr
    -0.39
    hassee
    -0.39
    aste
    -0.39
    PLIC
    -0.39
     pizza
    -0.38
    POSITIVE LOGITS
     LUMP
    0.69
    rzost
    0.63
    ServletException
    0.63
    Архівовано
    0.61
    TargetException
    0.58
     przesz
    0.58
    NUMX
    0.57
    AndEndTag
    0.57
    Specifiche
    0.57
    MemoryWarning
    0.57
    Activations Density 2.860%

    No Known Activations