© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11490
    Prev
    Next
    INDEX
    Explanations

    occurrences of the words "that", "what", "will", "caught", and "picture"

    oai_token-act-pair · gemini-2.0-flash

    strong opinions/emotions

    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
     nahilalakip
    -0.84
    fjspx
    -0.77
    Distribuzione
    -0.76
    ⓧ
    -0.76
     Administrativna
    -0.74
    FieldBuilder
    -0.72
    IntoConstraints
    -0.69
    makeText
    -0.68
    ReusableCell
    -0.66
    PreferredItem
    -0.65
    POSITIVE LOGITS
     Spitze
    0.45
    führer
    0.43
    ρες
    0.41
     Piggy
    0.40
    legs
    0.39
    ziom
    0.39
    )]$
    0.39
     gevallen
    0.39
     headings
    0.39
     *>
    0.38
    Activations Density 1.060%

    No Known Activations