© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1436
    Prev
    Next
    INDEX
    Explanations

    first person narration in past tense with additional qualifiers and modifiers

    oai_token-act-pair · gemini-2.0-flash

    had

    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
     unknownFields
    -0.82
    ArrowToggle
    -0.75
    нівер
    -0.75
     دیکھیے
    -0.75
     ProtoMessage
    -0.73
     PopupWindow
    -0.72
     ApiException
    -0.71
     demografica
    -0.71
     بيها
    -0.70
    =$?
    -0.69
    POSITIVE LOGITS
     had
    1.84
    Had
    1.54
    had
    1.54
     Had
    1.48
     HAD
    1.25
    HAD
    1.08
     hadde
    0.96
     hade
    0.93
     hadden
    0.92
     avait
    0.87
    Activations Density 1.488%

    No Known Activations