© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10208
    Prev
    Next
    INDEX
    Explanations

    descriptions of trails and outdoor areas

    oai_token-act-pair · gemini-2.0-flash

    walking trails

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     s
    -0.50
    т
    -0.46
     App
    -0.45
    OrBuilder
    -0.45
    a
    -0.44
    App
    -0.44
    2
    -0.44
     d
    -0.44
     t
    -0.43
     l
    -0.43
    POSITIVE LOGITS
     myſelf
    0.90
     متعلقه
    0.85
    IsContent
    0.81
     himſelf
    0.79
    MigrationBuilder
    0.79
     whoſe
    0.79
     مرئيه
    0.79
     themſelves
    0.78
     againſt
    0.77
     iſt
    0.77
    Activations Density 1.046%

    No Known Activations