© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14672
    Prev
    Next
    INDEX
    Explanations

    phrases related to a lack of control

    oai_token-act-pair · gemini-2.0-flash

    specific programming or technical terms

    np_token-act-pair-logits · gpt-4o-mini

    Being under control

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Control
    -0.56
    Control
    -0.56
     Controlled
    -0.48
     controlling
    -0.48
    fsch
    -0.47
     Controlling
    -0.46
    Revenir
    -0.46
    ingo
    -0.45
     CONTROL
    -0.45
     controlled
    -0.43
    POSITIVE LOGITS
     للاسماء
    0.92
    IndentedString
    0.82
     ModelExpression
    0.77
     Biôgrafia
    0.75
     tight
    0.75
     متعلقه
    0.74
    >*/
    0.73
    Rujuakan
    0.73
    exitRule
    0.71
    XmlEnum
    0.71
    Activations Density 1.121%

    No Known Activations