© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2517
    Prev
    Next
    INDEX
    Explanations

    words suggesting names of performances, festivals, films, theatrical works or other artistic productions.

    oai_token-act-pair · gemini-2.0-flash

    films

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     o
    -0.59
     #
    -0.51
     se
    -0.49
     M
    -0.48
    inka
    -0.47
     R
    -0.47
    kola
    -0.46
    defineProperty
    -0.46
     Mann
    -0.46
     me
    -0.45
    POSITIVE LOGITS
    ImageContext
    0.91
     createState
    0.90
    RenderAtEndOf
    0.78
     ―――――
    0.77
     Altri
    0.76
     Efq
    0.75
    MessageTagHelper
    0.73
    Personensuche
    0.71
     ſche
    0.71
     समीक्षक
    0.71
    Activations Density 1.896%

    No Known Activations