© 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. 11890
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers

    oai_token-act-pair · gemini-2.0-flash

    x

    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
    C
    -0.63
    A
    -0.59
    ształ
    -0.46
    .*,
    -0.42
    albero
    -0.42
    ggak
    -0.42
    B
    -0.40
    S
    -0.40
     magasiner
    -0.39
     المعرف
    -0.38
    POSITIVE LOGITS
     JpaRepository
    0.65
    IsContent
    0.63
     Bourgoin
    0.62
    WebVitals
    0.58
    2
    0.58
    rawDesc
    0.57
    wq
    0.57
    BeginContext
    0.57
    MemoryWarning
    0.56
    "}")
    0.56
    Activations Density 4.053%

    No Known Activations