© 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. 3020
    Prev
    Next
    INDEX
    Explanations

    first names with unusual letter combinations with activation increasing with name length

    oai_token-act-pair · gemini-2.0-flash

    European names/text

    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
    principalTable
    -0.81
    SourceChecksum
    -0.75
     للمعارف
    -0.73
    Portail
    -0.73
    IVEREF
    -0.71
    tagHelperRunner
    -0.71
     šķ
    -0.69
    TintMode
    -0.68
     <=",
    -0.67
    verwijspagina
    -0.66
    POSITIVE LOGITS
     K
    0.65
     Ko
    0.58
     Ku
    0.57
     Z
    0.56
     Dy
    0.55
     Bu
    0.55
     Klu
    0.54
     S
    0.52
     Kal
    0.52
     Kad
    0.51
    Activations Density 2.157%

    No Known Activations