© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11303
    Prev
    Next
    INDEX
    Explanations

    locations split by commas containing the words 'and', 'in', 'for', 'or' or words related to medical finances

    oai_token-act-pair · gemini-2.0-flash

    technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     maioria
    -1.45
     plupart
    -1.30
     meisten
    -1.29
    usually
    -1.29
     kebanyakan
    -1.28
     Often
    -1.27
     usually
    -1.27
     mayoría
    -1.26
    大多数
    -1.24
    Often
    -1.23
    POSITIVE LOGITS
     Tecn
    0.42
    >);
    0.41
    letterSpacing
    0.40
    kiwa
    0.38
    eczki
    0.38
    apor
    0.37
    inama
    0.36
    backers
    0.35
    ujudkan
    0.35
    ctors
    0.35
    Activations Density 2.227%

    No Known Activations