© 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. 14401
    Prev
    Next
    INDEX
    Explanations

    various markers in programming code, possible extracting API calls and job descriptions

    oai_token-act-pair · 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
    </h2>
    -2.23
    </h4>
    -2.17
    ")]
    -2.13
    "]
    -2.11
    "])
    -2.05
    </th>
    -2.03
    ']
    -1.98
    ")){
    -1.97
    "];
    -1.94
    "))
    -1.90
    POSITIVE LOGITS
     HasFactory
    0.48
    atecas
    0.47
    crites
    0.45
    ANCIA
    0.44
    lagio
    0.43
    ঙ্
    0.43
    apunov
    0.42
    ARAN
    0.42
    atás
    0.42
    שְׁ
    0.41
    Activations Density 0.316%

    No Known Activations