© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1801
    Prev
    Next
    INDEX
    Explanations

    words related to appearing in acting roles or media appearances

    oai_token-act-pair · gemini-2.0-flash

    Media appearances

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     appearance
    -2.47
     appear
    -2.44
     appears
    -2.30
     Appearance
    -2.11
     appearances
    -2.09
    appear
    -2.08
     APPE
    -2.06
    appears
    -2.03
     appearing
    -2.02
    appearance
    -2.00
    POSITIVE LOGITS
     propOrder
    0.77
    دانشنامهٔ
    0.71
    Datuak
    0.69
     تضيفلها
    0.65
    protoimpl
    0.64
     AssemblyCompany
    0.63
    enderror
    0.62
     "..\..\..\
    0.60
     ModelExpression
    0.59
    endpush
    0.58
    Activations Density 2.753%

    No Known Activations