© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15691
    Prev
    Next
    INDEX
    Explanations

    the prefix "tele-" and the word "defendant"

    oai_token-act-pair · gemini-2.0-flash

    tele

    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
     
    -0.68
    </tr>
    -0.60
     As
    -0.59
    ORTE
    -0.57
     ascorbic
    -0.57
     To
    -0.57
    ING
    -0.56
     The
    -0.56
     Electr
    -0.56
    ÉR
    -0.55
    POSITIVE LOGITS
    ViewFeatures
    1.01
     StatefulWidget
    0.96
     resourceCulture
    0.93
     initComponents
    0.90
     invokingState
    0.88
     AssemblyCulture
    0.84
    Życiorys
    0.84
    complexContent
    0.84
    TemporalType
    0.83
     betweenstory
    0.83
    Activations Density 1.387%

    No Known Activations