© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5380
    Prev
    Next
    INDEX
    Explanations

    subjective or personal statements

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    的最
    -0.70
     Most
    -0.68
     الأكثر
    -0.68
     najbolj
    -0.66
    Most
    -0.66
     máxima
    -0.65
    是最
    -0.64
    最
    -0.61
     najbol
    -0.61
     naj
    -0.60
    POSITIVE LOGITS
     the
    1.95
    the
    1.07
     THE
    0.65
    The
    0.64
    QMetaType
    0.63
    rethe
    0.63
    ithe
    0.60
     tbe
    0.60
    WireFormatLite
    0.57
    ザ
    0.57
    Activations Density 6.874%

    No Known Activations