© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12512
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and pronouns

    oai_token-act-pair · gemini-2.0-flash

    wasMethod: 1Reason: Could not determine any existing pattern.was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     bad
    -0.91
    bad
    -0.72
     BAD
    -0.68
    Bad
    -0.68
     Bad
    -0.68
    BAD
    -0.61
     worst
    -0.60
     stupid
    -0.58
     mauvais
    -0.57
     dumb
    -0.56
    POSITIVE LOGITS
     للاسماء
    0.94
     nahilalakip
    0.94
     nice
    0.88
     admirable
    0.87
     wonderful
    0.85
    aarrggbb
    0.84
    ValueStyle
    0.83
    GEBURTSDATUM
    0.82
     convertView
    0.82
     invokingState
    0.81
    Activations Density 1.633%

    No Known Activations