© 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. 3062
    Prev
    Next
    INDEX
    Explanations

    capitalized place names, especially cities and states, and references to news organizations

    oai_token-act-pair · gemini-2.0-flash

    locations

    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
     HasFactory
    -0.74
    TagMode
    -0.69
    RenderAtEndOf
    -0.66
     nakalista
    -0.64
    withIdentifier
    -0.57
    StructEnd
    -0.53
    #+#
    -0.52
    脚注の使い方
    -0.52
    исленность
    -0.52
    fjspx
    -0.51
    POSITIVE LOGITS
    EventLoop
    0.65
    Affirmed
    0.52
    GPP
    0.47
    ajur
    0.47
    unknownFields
    0.46
    hical
    0.45
    сылка
    0.45
    @[+][
    0.44
    response
    0.44
    ән
    0.44
    Activations Density 2.397%

    No Known Activations