© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13725
    Prev
    Next
    INDEX
    Explanations

    the beginning of direct quotes or turns in a conversation

    oai_token-act-pair · gemini-2.0-flash

    Interviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    <i>
    -0.99
    <code>
    -0.98
    </i>
    -0.93
    <sub>
    -0.91
    <b>
    -0.91
    <u>
    -0.87
     
    -0.84
    <em>
    -0.75
    </u>
    -0.74
    <s>
    -0.73
    POSITIVE LOGITS
    RegressionTest
    0.54
    posedge
    0.53
    minecraft
    0.50
    ManagedBean
    0.49
     Мекси
    0.46
    wpi
    0.44
    发表于
    0.43
     ??
    0.43
    र्भ
    0.43
     ویکی‌پدیا
    0.43
    Activations Density 2.896%

    No Known Activations