© 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. 128
    Prev
    Next
    INDEX
    Explanations

    uppercase words or acronyms sometimes followed by numbers or symbols in what appear to be code or legal documents

    oai_token-act-pair · gemini-2.0-flash

    Legal or technical documents

    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
    a
    -1.62
    i
    -1.39
    o
    -1.38
    e
    -1.36
    eer
    -1.02
    y
    -0.88
    ا
    -0.83
    ه
    -0.83
    oos
    -0.75
    aA
    -0.75
    POSITIVE LOGITS
    E
    0.73
    I
    0.71
    е
    0.69
    і
    0.66
    у
    0.61
    O
    0.58
    #+#
    0.58
    а
    0.56
    ECH
    0.54
    EAS
    0.53
    Activations Density 9.193%

    No Known Activations