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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15887
    Prev
    Next
    INDEX
    Explanations

    words having to do with seasonal changes or pagan traditions

    oai_token-act-pair · gemini-2.0-flash

    existence and spirituality

    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
     myſelf
    -0.96
     itſelf
    -0.95
     يتيمه
    -0.93
     Reſ
    -0.93
     houſe
    -0.91
     Jefus
    -0.90
     Monfieur
    -0.88
     pleaſure
    -0.87
     Majefty
    -0.86
     Eſ
    -0.85
    POSITIVE LOGITS
     hard
    0.53
     experienced
    0.52
    urez
    0.52
    .
    0.50
     Ver
    0.49
     deep
    0.49
     Du
    0.48
     zam
    0.47
    wiesen
    0.47
     du
    0.47
    Activations Density 16.562%

    No Known Activations