© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14146
    Prev
    Next
    INDEX
    Explanations

    partial words or character strings that are often parts of words.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     artificiales
    -0.56
     hyö
    -0.55
     osallist
    -0.53
     écout
    -0.50
     stället
    -0.50
     florales
    -0.50
     colorés
    -0.50
     rêves
    -0.49
     souffrance
    -0.49
     näky
    -0.48
    POSITIVE LOGITS
     sap
    0.43
     harp
    0.42
     archer
    0.42
     chameleon
    0.42
     kite
    0.41
     kiln
    0.41
     shank
    0.41
     jade
    0.41
     archers
    0.40
     mosaic
    0.40
    Activations Density 5.228%

    No Known Activations