© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2002
    Prev
    Next
    INDEX
    Explanations

    words related to American football and baseball sports

    oai_token-act-pair · gemini-2.0-flash

    technical or programming terms

    np_token-act-pair-logits · gpt-4o-mini

    sports and politics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    KommentareTeilen
    -0.52
     passado
    -0.49
    Filmographie
    -0.44
     originais
    -0.42
     Glass
    -0.41
    çais
    -0.41
     ailleurs
    -0.41
     Inner
    -0.39
    ้ว
    -0.39
    σχ
    -0.39
    POSITIVE LOGITS
    expandindo
    0.92
    IUrlHelper
    0.76
     Meksiku
    0.75
    UnknownFields
    0.75
    AsUp
    0.74
    WithIOException
    0.74
    ]")]
    0.73
    ForValue
    0.72
    WarningLevel
    0.71
    UnusedPrivate
    0.71
    Activations Density 0.857%

    No Known Activations