© 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. 14378
    Prev
    Next
    INDEX
    Explanations

    dates, locations, and names, frequently associated with number mentions, indicating a possible interest in event details or reports

    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
    Ещё
    -0.79
     fertiliser
    -0.77
     Initialise
    -0.77
     صوتيه
    -0.74
     Şi
    -0.73
    authorised
    -0.73
    alised
    -0.73
     realisation
    -0.72
     authorised
    -0.72
    Şi
    -0.72
    POSITIVE LOGITS
     favorite
    0.63
    favorite
    0.57
     theaters
    0.52
    ighbor
    0.51
     watercolor
    0.51
     favorably
    0.50
     favors
    0.50
     Inggris
    0.50
     Kilometer
    0.50
    hemo
    0.49
    Activations Density 13.135%

    No Known Activations