© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15968
    Prev
    Next
    INDEX
    Explanations

    parts of words starting with "rem" or bracketed letters

    oai_token-act-pair · gemini-2.0-flash

    fixing or remnants

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    DBNull
    -0.66
    QtWidgets
    -0.66
    fillType
    -0.65
     समीक्षाएं
    -0.64
    Geplaatst
    -0.63
     myſelf
    -0.63
    bitField
    -0.62
     itſelf
    -0.60
    AsUp
    -0.59
     hail
    -0.58
    POSITIVE LOGITS
    Демографія
    0.54
    issão
    0.51
    yarnpkg
    0.49
     vérit
    0.47
    KommentareTeilen
    0.47
     élector
    0.47
    addError
    0.46
    /**
    0.46
     ilmiah
    0.45
    度に
    0.43
    Activations Density 0.740%

    No Known Activations