© 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. 3481
    Prev
    Next
    INDEX
    Explanations

    mentions of the sun

    oai_token-act-pair · gemini-2.0-flash

    sun

    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
    PerformLayout
    -0.79
    原始内容存档于
    -0.71
     дописавши
    -0.69
    colgroup
    -0.69
     typelib
    -0.68
    WebVitals
    -0.66
    AnimationsModule
    -0.65
    RTEE
    -0.64
    TestingModule
    -0.64
    principalColumn
    -0.63
    POSITIVE LOGITS
    yon
    0.42
    anco
    0.42
    rat
    0.41
     ferons
    0.40
    yak
    0.40
     Sal
    0.40
     venons
    0.38
    BeginContext
    0.38
    Federation
    0.38
     Canaria
    0.37
    Activations Density 1.873%

    No Known Activations