© 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. 660
    Prev
    Next
    INDEX
    Explanations

    text with a high density of punctuation and other non-alphanumeric symbols

    oai_token-act-pair · gemini-2.0-flash

    dashes/quotes

    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
    Personendaten
    -0.71
    $")
    -0.68
    )*/
    -0.67
    Enllaces
    -0.66
     محفوظة
    -0.66
     Efq
    -0.62
    "],
    -0.61
    /*",
    -0.61
    ".
    -0.60
     архивлан
    -0.59
    POSITIVE LOGITS
    tesse
    0.52
    tetur
    0.50
    ussis
    0.46
    ட்ச
    0.45
    lexus
    0.45
    racuse
    0.45
    mpada
    0.43
    celotti
    0.42
    havi
    0.42
    rogels
    0.42
    Activations Density 7.230%

    No Known Activations