© 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. 12667
    Prev
    Next
    INDEX
    Explanations

    the word "craft"

    oai_token-act-pair · gemini-2.0-flash

    craft

    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
     ujednoznacz
    -0.90
     ComVisible
    -0.81
    SourceChecksum
    -0.81
    yntaxException
    -0.81
     Савезне
    -0.79
     disambiguazione
    -0.79
    cinogenicity
    -0.77
     Solicit
    -0.75
    skjaer
    -0.73
    Diweddarwch
    -0.71
    POSITIVE LOGITS
     kokona
    0.66
     piese
    0.57
     citoyens
    0.57
     behov
    0.56
     tjen
    0.55
     pysty
    0.54
     générations
    0.54
     alpina
    0.52
     abstracta
    0.52
    BeforeEach
    0.52
    Activations Density 1.286%

    No Known Activations