© 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. 9849
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to affection and physical intimacy, often in a romantic or sensual context.

    oai_token-act-pair · gemini-2.0-flash

    centers

    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
    Παραπομπές
    -0.60
    WriteAttribute
    -0.59
     }</
    -0.56
    =""></
    -0.55
    ScopeManager
    -0.53
     Bureau
    -0.52
    ()]);
    -0.51
    écri
    -0.50
    .*")]
    -0.50
     BUREAU
    -0.49
    POSITIVE LOGITS
     center
    0.75
    center
    0.75
     centre
    0.73
    insee
    0.68
     centers
    0.66
     centres
    0.65
    centre
    0.61
    Center
    0.61
    centers
    0.60
     TestBed
    0.59
    Activations Density 1.678%

    No Known Activations