© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4593
    Prev
    Next
    INDEX
    Explanations

    something bad or wrong by looking for issues or exceptions

    oai_token-act-pair · gemini-2.0-flash

    problems, issues, difficulties

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    krie
    -0.50
    GetAsync
    -0.47
     dover
    -0.47
     démocr
    -0.47
    tifiz
    -0.46
    viewers
    -0.46
    msgid
    -0.45
    %)$
    -0.44
    zelf
    -0.43
    ждународ
    -0.43
    POSITIVE LOGITS
    
    0.82
    Билгалдахарш
    0.73
    OGND
    0.73
     ProtoMessage
    0.69
    IsMutable
    0.65
     nahilalakip
    0.64
     opérés
    0.63
     كومونز
    0.62
    Autoritní
    0.61
    endregion
    0.57
    Activations Density 4.437%

    No Known Activations