© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12320
    Prev
    Next
    INDEX
    Explanations

    a person making an argument in the first-person, and possibly disagreeing with a group.

    oai_token-act-pair · gemini-2.0-flash

    I

    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
     Савезне
    -0.90
    AndEndTag
    -0.90
    tvguidetime
    -0.87
     MainAxisSize
    -0.85
    findpost
    -0.82
    StoryboardSegue
    -0.77
    Espèce
    -0.75
    хьтан
    -0.71
     LoggerFactory
    -0.70
    protoimpl
    -0.70
    POSITIVE LOGITS
     needed
    0.56
     are
    0.54
     but
    0.54
     necessary
    0.51
     learns
    0.48
    sum
    0.47
    liegen
    0.47
     Adamson
    0.46
     sum
    0.46
     attracts
    0.46
    Activations Density 9.547%

    No Known Activations