Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 994
    Prev
    Next
    INDEX
    Explanations

    scientific measurements of toxicity

    oai_token-act-pair · gemini-2.0-flash

    mass units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Datuak
    -0.86
     Paglinawan
    -0.77
    PhysRevD
    -0.76
    windowFixed
    -0.75
    bootstrapcdn
    -0.71
     '\\;'
    -0.68
    -};
    -0.67
    Identyfik
    -0.67
    +};
    -0.66
    thâu
    -0.66
    POSITIVE LOGITS
    defineProperty
    0.44
    Parents
    0.43
     Painters
    0.43
    cinia
    0.43
     Parents
    0.41
    mtrl
    0.40
    irc
    0.39
    Derived
    0.39
    ָה
    0.39
    τ
    0.38
    Activations Density 3.720%

    No Known Activations