© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13558
    Prev
    Next
    INDEX
    Explanations

    emotional words of difficulty and hardship

    oai_token-act-pair · gemini-2.0-flash

    positive adjectives

    np_max-act-logits · 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
    AndEndTag
    -0.78
     betweenstory
    -0.68
    LookAnd
    -0.66
     الرياضيه
    -0.65
    enderror
    -0.65
    setVerticalGroup
    -0.64
    SequentialGroup
    -0.63
     ModelExpression
    -0.63
    :✨
    -0.62
    QUENCE
    -0.62
    POSITIVE LOGITS
     taxing
    0.59
     soul
    0.56
     fulfilling
    0.55
     arresting
    0.54
     rewarding
    0.54
     convic
    0.53
     illuminating
    0.53
     enriching
    0.51
     warming
    0.50
     satisfying
    0.49
    Activations Density 1.921%

    No Known Activations