© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4173
    Prev
    Next
    INDEX
    Explanations

    the word "garage" and related words

    oai_token-act-pair · gemini-2.0-flash

    garage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    casian
    -0.67
    Aiheesta
    -0.64
     strumento
    -0.64
    hoea
    -0.63
    oader
    -0.61
    rawDesc
    -0.60
     bezit
    -0.58
    bentar
    -0.57
    profen
    -0.57
    jspx
    -0.55
    POSITIVE LOGITS
     Theſe
    0.84
     Efq
    0.82
    .)}
    0.82
     Beſ
    0.81
    expandindo
    0.81
    ...');
    0.81
     leaſt
    0.80
     itſelf
    0.80
     chofe
    0.79
     pleaſure
    0.79
    Activations Density 0.299%

    No Known Activations