© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4792
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to investigations, politics, and government

    oai_token-act-pair · gemini-2.0-flash

    possessive determiners

    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
    I
    -0.43
    T
    -0.42
    There
    -0.36
    ToTable
    -0.35
    OutOfRange
    -0.35
    irs
    -0.35
    országban
    -0.35
    U
    -0.34
    běh
    -0.34
    C
    -0.34
    POSITIVE LOGITS
     the
    1.38
     your
    1.16
     his
    1.16
     our
    1.06
     those
    0.97
     these
    0.93
     their
    0.85
     her
    0.83
     theſe
    0.82
     Efq
    0.82
    Activations Density 9.471%

    No Known Activations