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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11280
    Prev
    Next
    INDEX
    Explanations

    words that describe the physical state of a room and/or items in a room.

    oai_token-act-pair · gemini-2.0-flash

    unusual or technical terms

    np_token-act-pair-logits · gpt-4o-mini

    Interior design/flooring

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Air
    -0.42
    mbg
    -0.41
     Gén
    -0.40
    項
    -0.38
     Rial
    -0.38
    Air
    -0.38
     figure
    -0.37
    tagHelper
    -0.36
     Swift
    -0.36
     acar
    -0.36
    POSITIVE LOGITS
    Autoritní
    0.82
    GEBURTSDATUM
    0.80
    σιμοποι
    0.76
    Билгалдахарш
    0.74
     mergeFrom
    0.73
    antMatchers
    0.73
    FormTagHelper
    0.72
    ########.
    0.71
    DockStyle
    0.70
    errHandler
    0.66
    Activations Density 1.354%

    No Known Activations