© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12651
    Prev
    Next
    INDEX
    Explanations

    words relating to people

    oai_token-act-pair · gemini-2.0-flash

    seeing people

    np_max-act-logits · gemini-2.0-flash

    say "ending -ing" Method used: 2 — because following tokens are largely "-ing" verbs

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    LabelTagHelper
    -0.54
     siège
    -0.47
     '\\;'
    -0.47
     cál
    -0.42
    省市镇
    -0.42
     DELIVER
    -0.41
    henswürdigkeiten
    -0.41
    gwin
    -0.40
    Välislingid
    -0.40
     ADVANCED
    -0.39
    POSITIVE LOGITS
     Majefty
    0.73
     initComponents
    0.66
    ſelf
    0.64
    (;;)
    0.63
     wearing
    0.62
    Written
    0.61
     يتيمه
    0.61
     clad
    0.60
     rospy
    0.60
     myſelf
    0.58
    Activations Density 4.100%

    No Known Activations