© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9373
    Prev
    Next
    INDEX
    Explanations

    question words and punctuation marks

    oai_token-act-pair · gemini-2.0-flash

    the word "what"

    np_token-act-pair-logits · gpt-4o-mini

    what

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Hentet
    -0.60
     CreateTagHelper
    -0.56
     ModelExpression
    -0.55
    UnusedPrivate
    -0.53
     PyLong
    -0.52
    Told
    -0.50
    RuleContext
    -0.49
    
    -0.48
    GenerationType
    -0.48
    fromnode
    -0.48
    POSITIVE LOGITS
    MENAFN
    0.65
     مشين
    0.61
     חיצוניים
    0.60
    DrawerLayout
    0.59
     ligiloj
    0.57
    abou
    0.57
     happens
    0.57
    expandindo
    0.55
     counts
    0.55
     happened
    0.54
    Activations Density 0.626%

    No Known Activations