© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 682
    Prev
    Next
    INDEX
    Explanations

    instances where the author is seeking advice or insight, particularly when posing questions or expressing uncertainty about what actions they can take

    oai_token-act-pair · gemini-2.0-flash

    Questions or requests

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     reason
    -1.87
     reasons
    -1.67
    reason
    -1.55
    reasons
    -1.51
    Reasons
    -1.46
    Reason
    -1.45
     Reasons
    -1.44
     Reason
    -1.41
     REASONS
    -1.32
     raisons
    -1.30
    POSITIVE LOGITS
     can
    0.58
    cipy
    0.50
     could
    0.49
    SourceChecksum
    0.48
     légales
    0.47
     ChromeDriver
    0.46
     resourceCulture
    0.44
    älde
    0.44
     actionPerformed
    0.42
     TestCase
    0.42
    Activations Density 0.447%

    No Known Activations