© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9550
    Prev
    Next
    INDEX
    Explanations

    references to sequential ordering in space or time

    oai_token-act-pair · gemini-2.0-flash

    order, steps, sequence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -0.73
     néz
    -0.65
     חיצוניים
    -0.64
    věr
    -0.63
    adaptiveStyles
    -0.60
     صوتيه
    -0.57
     itinéraires
    -0.55
     wireType
    -0.54
    Derbyniad
    -0.54
    onOptions
    -0.53
    POSITIVE LOGITS
    Pants
    0.56
    Bronnen
    0.55
     endwhile
    0.55
    างเกง
    0.55
    dfunding
    0.55
    Doh
    0.54
     NDEBUG
    0.54
     Vittoria
    0.52
    Примітки
    0.51
    ISupport
    0.51
    Activations Density 0.277%

    No Known Activations