© 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. 974
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    computer code

    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
    :+:
    -0.73
    Datuak
    -0.58
    !*\
    -0.57
     '{@
    -0.57
    SPJ
    -0.56
    Попис
    -0.56
    :][
    -0.55
    uisine
    -0.54
    Rptr
    -0.53
    marshaller
    -0.52
    POSITIVE LOGITS
     AssertionError
    0.54
    etter
    0.53
    er
    0.51
     preuves
    0.50
    RowCount
    0.50
    bai
    0.49
    neh
    0.47
    nea
    0.47
    tive
    0.47
    moni
    0.46
    Activations Density 3.381%

    No Known Activations