© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8486
    Prev
    Next
    INDEX
    Explanations

    text related to law enforcement divisions and mental health services

    oai_token-act-pair · gemini-2.0-flash

    specialized case management terminology

    np_token-act-pair-logits · gpt-4o-mini

    law enforcement and legal processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    JspWriter
    -0.68
     anhyd
    -0.68
    SEGUIR
    -0.66
    sidemargin
    -0.63
    VersionUID
    -0.63
    WithIOException
    -0.63
    
    -0.62
    Билгалдахарш
    -0.60
    varargin
    -0.60
    最快更新
    -0.59
    POSITIVE LOGITS
    督
    0.44
     K
    0.44
     koń
    0.43
    Smarty
    0.42
     Seconde
    0.42
     désolés
    0.42
     plain
    0.41
    jdt
    0.41
    kega
    0.41
    stanford
    0.41
    Activations Density 0.858%

    No Known Activations