© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12259
    Prev
    Next
    INDEX
    Explanations

    the context around technical needs, specifically those related to computer game design

    oai_token-act-pair · gemini-2.0-flash

    OpenGL, programming code

    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
     Parcelable
    -0.80
    pexpr
    -0.78
    KommentareTeilen
    -0.76
    клопе
    -0.75
    ChildScrollView
    -0.74
     useNavigate
    -0.70
    afficheront
    -0.70
    prepareStatement
    -0.68
    зулта
    -0.67
    Архівовано
    -0.67
    POSITIVE LOGITS
     tevreden
    0.45
     générations
    0.44
     normaux
    0.44
     retrovisor
    0.42
     circonstances
    0.42
    hynch
    0.41
     amarillas
    0.41
     Boyce
    0.40
     kommune
    0.39
     verksamhet
    0.39
    Activations Density 1.017%

    No Known Activations