© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4445
    Prev
    Next
    INDEX
    Explanations

    structural parts of a paper, like section numbers, figure references, keywords, or introductions

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    reactstrap
    -0.65
    ⓧ
    -0.55
     Cell
    -0.48
    stateProvider
    -0.46
    Cell
    -0.46
     %>%
    -0.45
     epa
    -0.44
    CROSSTALK
    -0.43
    tokine
    -0.42
    ando
    -0.42
    POSITIVE LOGITS
     للاسماء
    0.73
    Chham
    0.70
    VersionUID
    0.63
    prefixer
    0.61
    posób
    0.58
    #+#
    0.58
    eseorang
    0.57
    ingeki
    0.53
    !]
    0.51
    imarães
    0.51
    Activations Density 2.651%

    No Known Activations