© 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. 7340
    Prev
    Next
    INDEX
    Explanations

    common English words.

    oai_token-act-pair · gemini-2.0-flash

    more

    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
     snippetHide
    -0.83
     '\\;'
    -0.70
    Better
    -0.68
    Greater
    -0.66
    脚注の使い方
    -0.66
     Better
    -0.66
    Larger
    -0.65
     Larger
    -0.65
     onPostExecute
    -0.64
     coarser
    -0.63
    POSITIVE LOGITS
     more
    2.67
    more
    2.02
    More
    1.94
     More
    1.80
     mehr
    1.53
     MORE
    1.53
     más
    1.50
     più
    1.45
     более
    1.44
     lebih
    1.32
    Activations Density 15.681%

    No Known Activations