© 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-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11635
    Prev
    Next
    INDEX
    Explanations

    various code snippets, particularly javascript and/or pieces of mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    AutoScaleMode
    -0.72
    οιν
    -0.67
     Bohemia
    -0.65
    υτό
    -0.63
    drawSprites
    -0.61
    WithMany
    -0.61
    
    -0.61
     Spence
    -0.60
     <<<<<<<<<<<<<<
    -0.60
    Là
    -0.60
    POSITIVE LOGITS
    NOPQRST
    0.59
    RenderAtEndOf
    0.43
    Bibliograf
    0.43
     ThemeData
    0.41
     initComponents
    0.40
    TargetException
    0.40
    sidemargin
    0.40
     grève
    0.38
     zpra
    0.38
     arcilla
    0.38
    Activations Density 2.114%

    No Known Activations