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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2474
    Prev
    Next
    INDEX
    Explanations

    a mix of words that could be used when discussing conflict, Harry Potter and money

    oai_token-act-pair · gemini-2.0-flash

    issue/issues

    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
    تقاوى
    -0.91
     Paglinawan
    -0.75
     difficulty
    -0.69
     дописавши
    -0.66
    InSection
    -0.65
    difficulty
    -0.64
    featureID
    -0.63
    diffic
    -0.63
    Solución
    -0.63
    +#+#
    -0.61
    POSITIVE LOGITS
     issue
    2.53
     issues
    2.44
    issue
    2.31
     Issue
    2.23
    Issue
    2.20
     Issues
    2.20
    issues
    2.19
    Issues
    2.06
     ISSUE
    2.05
     ISSUES
    1.95
    Activations Density 8.239%

    No Known Activations