© 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. 15218
    Prev
    Next
    INDEX
    Explanations

    technical paragraphs with numbers and units of measurement

    oai_token-act-pair · gemini-2.0-flash

    dollar sign

    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
     ‘
    -2.06
    ‘
    -2.06
    ’
    -2.02
    …’
    -1.81
     ‚
    -1.80
     ’
    -1.78
     ‘‘
    -1.74
     ‘’
    -1.72
    (‘
    -1.70
     
    -1.70
    POSITIVE LOGITS
     $
    1.23
     $\$
    0.85
    $
    0.79
     $(
    0.72
     ${
    0.67
     $\
    0.66
    .$
    0.65
     $/
    0.64
     $-
    0.61
     $+
    0.60
    Activations Density 6.775%

    No Known Activations