© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6158
    Prev
    Next
    INDEX
    Explanations

    names of people, sometimes including middle initials or titles

    oai_token-act-pair · gemini-2.0-flash

    Fl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Efq
    -0.79
    ########.
    -0.74
    URLException
    -0.74
     Wikimedijinoj
    -0.72
    bootstrapcdn
    -0.63
     arşivlendi
    -0.61
     chofe
    -0.60
     تانيه
    -0.60
    PhysRev
    -0.60
    لينكات
    -0.60
    POSITIVE LOGITS
    InSection
    0.50
    EDEFAULT
    0.49
    脚注の使い方
    0.47
    urier
    0.43
    ViewImports
    0.43
    eclamp
    0.43
    ftagPool
    0.42
    出自
    0.41
     calendriers
    0.41
    cshtml
    0.40
    Activations Density 1.177%

    No Known Activations