© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11100
    Prev
    Next
    INDEX
    Explanations

    explicit references to currency

    oai_token-act-pair · gemini-2.0-flash

    currencies

    np_max-act · gemini-2.0-flash

    currencies

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     يتيمه
    -0.89
     مشين
    -0.70
    providedIn
    -0.70
    
    -0.66
    Referències
    -0.64
    깥
    -0.63
     lenker
    -0.60
    ativistic
    -0.59
    rungsseite
    -0.59
    __(/*!
    -0.59
    POSITIVE LOGITS
     £
    0.99
    <bos>
    0.96
    £
    0.88
     ₹
    0.83
     dollars
    0.79
     dollar
    0.77
     (£
    0.75
     cash
    0.75
     €
    0.74
     Rs
    0.74
    Activations Density 0.631%

    No Known Activations