© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11618
    Prev
    Next
    INDEX
    Explanations

    the prefix "sy"

    oai_token-act-pair · gemini-2.0-flash

    Sy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    errHandler
    -0.92
     propOrder
    -0.91
    Personendaten
    -0.90
    ///</
    -0.88
    Gön
    -0.86
     utafitiHapana
    -0.85
    findpost
    -0.85
    aarrggbb
    -0.81
    protoimpl
    -0.81
    SourceChecksum
    -0.79
    POSITIVE LOGITS
    Skocz
    0.46
    бки
    0.38
    nthesis
    0.37
    landa
    0.37
    llen
    0.36
    íncia
    0.35
    Hochspringen
    0.35
    tsy
    0.34
    rett
    0.33
    uz
    0.33
    Activations Density 1.281%

    No Known Activations