© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11255
    Prev
    Next
    INDEX
    Explanations

    text pertaining to Tetsuya Nakashima, a Japanese film director, specifically references to his birth and work history.

    oai_token-act-pair · gemini-2.0-flash

    locations in Japan

    np_token-act-pair-logits · gpt-4o-mini

    Japan

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    InitVars
    -0.83
     betweenstory
    -0.80
    BeginInit
    -0.79
    LookAnd
    -0.79
     autorytatywna
    -0.79
     Réponses
    -0.77
     ligiloj
    -0.76
    AddTagHelper
    -0.72
    StoryboardSegue
    -0.71
    日閲覧
    -0.69
    POSITIVE LOGITS
     BoxDecoration
    0.46
    minde
    0.42
     skry
    0.41
     kanssa
    0.38
    min
    0.34
    esp
    0.33
     henkil
    0.33
    SECONDS
    0.33
     động
    0.32
     étend
    0.32
    Activations Density 0.438%

    No Known Activations