© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16370
    Prev
    Next
    INDEX
    Explanations

    angle bracket and curly brace combinations in code and HTML

    oai_token-act-pair · gemini-2.0-flash

    syntax characters

    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
    })`
    -0.89
    tagHelperRunner
    -0.88
    #
    -0.85
    MigrationBuilder
    -0.82
    }(),
    -0.81
    })->
    -0.80
    JspWriter
    -0.80
    InitVars
    -0.79
    >(),
    -0.78
    /*
    -0.78
    POSITIVE LOGITS
    .
    0.75
    ’
    0.65
    shutil
    0.60
    ,
    0.56
     nélk
    0.52
    routeProvider
    0.51
     bodyParser
    0.46
    abcdefghijklmnop
    0.45
    propan
    0.45
    igshid
    0.45
    Activations Density 2.805%

    No Known Activations