© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4596
    Prev
    Next
    INDEX
    Explanations

    technical writing that uses mathematical or scientific models and analysis, especially related to data and simulations.

    oai_token-act-pair · gemini-2.0-flash

    research publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    脚注の使い方
    -1.07
    DockStyle
    -1.02
     CreateTagHelper
    -1.01
     وتسجيلات
    -0.92
    ագրություններ
    -0.92
    
    -0.91
    enumii
    -0.91
     feroit
    -0.89
     itſelf
    -0.89
     متعلقه
    -0.88
    POSITIVE LOGITS
     to
    0.50
     San
    0.46
     model
    0.44
    …
    0.44
    ...
    0.44
    gen
    0.44
     in
    0.43
     till
    0.43
    BL
    0.43
     is
    0.42
    Activations Density 11.978%

    No Known Activations