© 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. 12188
    Prev
    Next
    INDEX
    Explanations

    words, phrases, formatting and punctuation related to lists of facts

    oai_token-act-pair · gemini-2.0-flash

    Sports and countries

    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
    principalColumn
    -0.91
     autorytatywna
    -0.82
    GraphicsUnit
    -0.81
     disambiguazione
    -0.70
    aarrggbb
    -0.69
     Signalez
    -0.66
    tagHelperRunner
    -0.66
    Xna
    -0.65
    
    -0.65
    Geplaatst
    -0.64
    POSITIVE LOGITS
    OrWhiteSpace
    0.46
    ính
    0.45
     pēc
    0.42
     new
    0.41
    собенности
    0.41
    ٬
    0.40
     służ
    0.40
     target
    0.40
    Variety
    0.40
    서는
    0.40
    Activations Density 2.333%

    No Known Activations