© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15256
    Prev
    Next
    INDEX
    Explanations

    mentions of random people, especially in the context of stories or groups.

    oai_token-act-pair · gemini-2.0-flash

    Groups of people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    GraphicsUnit
    -0.77
     viewType
    -0.76
     utafitiHapana
    -0.75
     nakalista
    -0.74
     EconPapers
    -0.74
     cdti
    -0.73
     itſelf
    -0.71
     Argos
    -0.69
     typelib
    -0.69
     Baal
    -0.68
    POSITIVE LOGITS
    Everybody
    0.69
     Everybody
    0.68
     everybody
    0.67
    --
    0.59
    Anybody
    0.57
     somebody
    0.56
    ——
    0.55
     anybody
    0.55
    —
    0.55
     isn
    0.54
    Activations Density 4.753%

    No Known Activations