© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3738
    Prev
    Next
    INDEX
    Explanations

    the name "Iluobe" and related context like "Chief" and "JP"

    oai_token-act-pair · gemini-2.0-flash

    Dense complex passages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    WebVitals
    -0.57
     EconPapers
    -0.48
     Springsteen
    -0.47
     Hughes
    -0.46
     Browns
    -0.46
    textLabel
    -0.46
    รส
    -0.44
    ضع
    -0.44
     Arrows
    -0.44
     Whites
    -0.44
    POSITIVE LOGITS
     незавершена
    0.68
    viewDidLoad
    0.64
    CopyWith
    0.63
    ReusableCell
    0.54
    новниш
    0.54
    #
    0.52
    ruptedException
    0.51
    RectangleBorder
    0.51
    manteau
    0.51
    각주
    0.50
    Activations Density 12.447%

    No Known Activations