© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3720
    Prev
    Next
    INDEX
    Explanations

    intensifiers and words about feelings

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    flashdata
    -0.63
     eccl
    -0.58
    Diwedd
    -0.53
     inconn
    -0.52
     tantum
    -0.51
    addPreferredGap
    -0.51
    razza
    -0.50
    ESPEC
    -0.49
    énération
    -0.47
     aspetta
    -0.46
    POSITIVE LOGITS
     kaarangay
    0.78
    تقاوى
    0.75
     CreateTagHelper
    0.67
     mergeFrom
    0.67
    parsedMessage
    0.66
    
    0.60
     समीक्षाओं
    0.59
    opencv
    0.59
     ModelExpression
    0.58
    featureID
    0.57
    Activations Density 0.613%

    No Known Activations