© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3700
    Prev
    Next
    INDEX
    Explanations

    the numerical sequence 2234 followed by a slash and then the number 7.

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the number seven

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

    time/dates

    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
    jgl
    -0.70
    esModule
    -0.58
     EconPapers
    -0.58
    APOLIS
    -0.58
     createState
    -0.57
    MLLoader
    -0.54
    IsContent
    -0.52
     réessayer
    -0.52
    TagHelper
    -0.50
    __':
    -0.49
    POSITIVE LOGITS
    SEVEN
    0.64
     Seven
    0.63
    Personensuche
    0.58
     SEVEN
    0.58
    endphp
    0.56
    Seven
    0.56
     Eleven
    0.54
    ⋙
    0.54
     étend
    0.54
    Eleven
    0.52
    Activations Density 0.946%

    No Known Activations