© 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. 14242
    Prev
    Next
    INDEX
    Explanations

    words that appear to be from a language other than English

    oai_token-act-pair · gemini-2.0-flash

    Multiple Language, Code Snippets

    np_max-act-logits · 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
    heten
    -0.63
     refroidissement
    -0.54
     suprême
    -0.53
     frumos
    -0.53
     diaphragm
    -0.52
    ranean
    -0.50
     novin
    -0.50
     réfrig
    -0.50
    ophanes
    -0.50
     conmigo
    -0.48
    POSITIVE LOGITS
    abestanden
    0.67
    PerformLayout
    0.66
    )):
    0.54
     تضيفلها
    0.53
     Waray
    0.52
     Desk
    0.51
    enderror
    0.50
    )?;
    0.50
    DockStyle
    0.49
     createSlice
    0.48
    Activations Density 0.458%

    No Known Activations