© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8025
    Prev
    Next
    INDEX
    Explanations

    sentences containing multiple auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    something becomes clear

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     clearly
    -2.03
    clearly
    -1.96
     Clearly
    -1.82
    Clearly
    -1.70
     clairement
    -1.49
     chiaramente
    -1.46
     claramente
    -1.41
     plainly
    -1.20
     duidelijk
    -1.02
     jelas
    -0.97
    POSITIVE LOGITS
     bianche
    0.46
    ^{+}
    0.44
    presto
    0.42
    衛門
    0.41
    ecycle
    0.41
     Slater
    0.40
    incón
    0.40
     censi
    0.40
    eves
    0.40
     zap
    0.40
    Activations Density 13.756%

    No Known Activations