© 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. 16232
    Prev
    Next
    INDEX
    Explanations

    prepositions and other grammatical function words

    oai_token-act-pair · gemini-2.0-flash

    by

    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
    ,
    -0.50
    It
    -0.44
    2
    -0.42
    By
    -0.42
    (
    -0.40
    .
    -0.39
    mu
    -0.39
    He
    -0.38
     by
    -0.37
    D
    -0.36
    POSITIVE LOGITS
     XCTest
    0.82
    othek
    0.82
    migrationBuilder
    0.78
    ArgsConstructor
    0.77
    webElementGuid
    0.77
    polation
    0.77
    setVerticalGroup
    0.76
    oredCriteria
    0.76
     незавершена
    0.75
    HICLE
    0.73
    Activations Density 26.172%

    No Known Activations