© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14893
    Prev
    Next
    INDEX
    Explanations

    numerical ratios and proportions

    oai_token-act-pair · gemini-2.0-flash

    hyphens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     незавершена
    -0.62
    !*\
    -0.56
    phazard
    -0.55
    QMetaType
    -0.54
     ProtoMessage
    -0.51
    complexType
    -0.51
     <=",
    -0.50
    ATURE
    -0.49
     compromis
    -0.48
    spesies
    -0.46
    POSITIVE LOGITS
    Hozzáférés
    0.63
     StringUtil
    0.59
    endpush
    0.56
     Diman
    0.55
    Tikang
    0.55
     verdens
    0.54
     døde
    0.54
     Somer
    0.54
    #
    0.53
     NgModule
    0.53
    Activations Density 2.943%

    No Known Activations