© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15645
    Prev
    Next
    INDEX
    Explanations

    text from accounting service adverts.

    oai_token-act-pair · gemini-2.0-flash

    professional contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     مرئيه
    -0.96
    ruptedException
    -0.71
    GraphicsUnit
    -0.69
     محفوظة
    -0.67
     ویکی‌پدیای
    -0.61
     juridiques
    -0.60
     SafeMath
    -0.60
    Муж
    -0.59
    TextWatcher
    -0.58
     culturelles
    -0.58
    POSITIVE LOGITS
     top
    0.52
    Datuak
    0.48
    IDENTAL
    0.46
     full
    0.46
    zegovina
    0.45
    вой
    0.44
     researchers
    0.43
     administrators
    0.43
     investigators
    0.43
    meral
    0.43
    Activations Density 4.122%

    No Known Activations