© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10294
    Prev
    Next
    INDEX
    Explanations

    terms related to software businesses, blogging, and marketing.

    oai_token-act-pair · gemini-2.0-flash

    blogging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    leyebilirsiniz
    -0.66
    .}(
    -0.64
    endphp
    -0.64
     setuptools
    -0.63
    <bos>
    -0.61
    rinfo
    -0.59
    }$_
    -0.59
    }}^{(
    -0.59
    .*")]
    -0.58
    maths
    -0.56
    POSITIVE LOGITS
    findpost
    0.55
    EDEFAULT
    0.47
     препратки
    0.44
    RunAsync
    0.44
     հղումներ
    0.44
    addGap
    0.41
     peix
    0.41
    UnusedPrivate
    0.41
    andaag
    0.39
    elry
    0.39
    Activations Density 2.090%

    No Known Activations