© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12211
    Prev
    Next
    INDEX
    Explanations

    social interactions, relationships, and shared experiences, possibly with an emphasis on those that are positive or worth pursuing.

    oai_token-act-pair · gemini-2.0-flash

    get

    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
    PreferredItem
    -0.71
    MigrationBuilder
    -0.70
    ьаж
    -0.67
    Билгалдахарш
    -0.67
     oprot
    -0.66
    msgTypes
    -0.66
    writeFieldEnd
    -0.66
     ***!
    -0.65
     الرياضيه
    -0.65
    AnchorStyles
    -0.65
    POSITIVE LOGITS
     get
    1.85
     getting
    1.82
     Getting
    1.70
    Getting
    1.60
     Get
    1.60
    get
    1.59
     gets
    1.58
    getting
    1.53
    Get
    1.52
     GETTING
    1.48
    Activations Density 2.193%

    No Known Activations