© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15516
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns, especially when used to express a desire or recounting personal experience

    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_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
     Qo
    -0.59
     OBITUARY
    -0.54
     sasuke
    -0.53
     IRIS
    -0.52
     Cæsar
    -0.52
     Mgr
    -0.52
    сылкі
    -0.50
    TypedDataSet
    -0.50
     pct
    -0.49
    què
    -0.49
    POSITIVE LOGITS
     BoxFit
    0.79
    HasForeignKey
    0.66
    AnchorStyles
    0.62
    expandindo
    0.58
     ***!
    0.50
    MENAFN
    0.49
    पया
    0.47
    StatusBadRequest
    0.46
    glVertex
    0.46
    InSection
    0.45
    Activations Density 1.604%

    No Known Activations