© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11416
    Prev
    Next
    INDEX
    Explanations

    the word "spirit" and related terms having positive connotations.

    oai_token-act-pair · gemini-2.0-flash

    spirit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ]")]
    -0.99
     itſelf
    -0.89
     Houſe
    -0.86
     Theſe
    -0.86
     Diſ
    -0.76
     Reſ
    -0.76
     Anſ
    -0.76
     Jefus
    -0.75
     Conſ
    -0.75
    ſelves
    -0.75
    POSITIVE LOGITS
    complishments
    0.63
    fortun
    0.63
     atrap
    0.58
    strophic
    0.57
    ाई
    0.57
     unable
    0.57
     Groß
    0.56
     proud
    0.56
     asume
    0.56
    InThe
    0.55
    Activations Density 1.098%

    No Known Activations