© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 57
    Prev
    Next
    INDEX
    Explanations

    code snippets and file paths.

    oai_token-act-pair · gemini-2.0-flash

    letter E

    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
     e
    -1.17
    e
    -0.82
    eg
    -0.77
     eg
    -0.74
     et
    -0.73
     ed
    -0.62
     ee
    -0.59
     er
    -0.59
    et
    -0.57
    ee
    -0.56
    POSITIVE LOGITS
    E
    0.92
     E
    0.85
     Э
    0.80
    Ｅ
    0.80
     Е
    0.72
    𝐸
    0.69
    Э
    0.68
     Eo
    0.67
     EJ
    0.66
     ESE
    0.66
    Activations Density 2.750%

    No Known Activations