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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6211
    Prev
    Next
    INDEX
    Explanations

    characters from various non-English languages and possibly escape characters

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     يتيمه
    -0.50
    zeß
    -0.49
    .~(\
    -0.47
    [];
    -0.46
    [
    -0.45
    GraphicsUnit
    -0.45
     away
    -0.44
    [])
    -0.44
     fortunately
    -0.43
     """",
    -0.43
    POSITIVE LOGITS
    AsUp
    0.76
     pulumi
    0.62
     autorytatywna
    0.61
     चीज़ों
    0.59
    cipar
    0.59
    TargetApi
    0.59
     ویکی‌پدیای
    0.59
     ویکی‌پدی
    0.58
    Datuak
    0.56
    ########.
    0.56
    Activations Density 12.860%

    No Known Activations