© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15162
    Prev
    Next
    INDEX
    Explanations

    references to accounting firms and financial regulation.

    oai_token-act-pair · gemini-2.0-flash

    financial misconduct and penalties

    np_token-act-pair-logits · gpt-4o-mini

    Auditing and taxes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    참고
    -0.57
    Single
    -0.55
    Хьажоргаш
    -0.54
    OGND
    -0.53
    ModelAdmin
    -0.52
     beginnetje
    -0.50
     Single
    -0.49
    TagMode
    -0.49
    single
    -0.48
     onCreateView
    -0.47
    POSITIVE LOGITS
    Abitanti
    0.66
     Houſe
    0.59
    ſelves
    0.59
     Majefty
    0.54
     myſelf
    0.52
     kontaktu
    0.52
     vár
    0.51
    ofman
    0.50
     Reco
    0.50
    )");
    0.50
    Activations Density 1.394%

    No Known Activations