© 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. 10129
    Prev
    Next
    INDEX
    Explanations

    words starting with the capital letter "T" that occur in legal or criminal contexts

    oai_token-act-pair · gemini-2.0-flash

    Tongo or Katanga

    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
     nahilalakip
    -0.89
     CreateTagHelper
    -0.75
     betweenstory
    -0.74
    XmlAccessType
    -0.72
    GraphicsUnit
    -0.69
    InjectAttribute
    -0.69
    )++;
    -0.67
    ExtendWith
    -0.67
    ГЛА
    -0.67
    XmlEnum
    -0.66
    POSITIVE LOGITS
    Object
    0.44
    object
    0.44
    Objects
    0.41
     rodi
    0.41
    jatel
    0.39
    тивным
    0.39
    str
    0.38
     rivel
    0.38
    culada
    0.37
     imposible
    0.36
    Activations Density 0.231%

    No Known Activations