© 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. 3511
    Prev
    Next
    INDEX
    Explanations

    the word "Van"

    oai_token-act-pair · gemini-2.0-flash

    van

    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
     StringTokenizer
    -0.55
    صل
    -0.54
     scarcity
    -0.51
     méri
    -0.49
     Varsity
    -0.49
    
    -0.48
     Caro
    -0.46
     verzorg
    -0.45
     lobes
    -0.45
     homologous
    -0.45
    POSITIVE LOGITS
     intptr
    0.69
    aarrggbb
    0.68
     חיצוניים
    0.67
    Välislingid
    0.65
     estekak
    0.65
     typelib
    0.64
    uxxxx
    0.60
    LookAnd
    0.60
    awtextra
    0.59
    Tikang
    0.58
    Activations Density 0.298%

    No Known Activations