© 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. 9871
    Prev
    Next
    INDEX
    Explanations

    instances of "more," sometimes in conjunction with related words like "extra."

    oai_token-act-pair · gemini-2.0-flash

    More

    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
    Further
    -0.51
    further
    -0.49
     vecka
    -0.45
     Further
    -0.45
     further
    -0.43
    الإنجليزية
    -0.40
     molte
    -0.39
     wielu
    -0.39
    several
    -0.39
     muchas
    -0.39
    POSITIVE LOGITS
    ########.
    0.75
     EconPapers
    0.65
    esez
    0.64
     EClass
    0.60
    thâu
    0.60
    OGND
    0.59
    Batis
    0.59
    XmlType
    0.59
    saraba
    0.59
    <bos>
    0.58
    Activations Density 3.700%

    No Known Activations