© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11737
    Prev
    Next
    INDEX
    Explanations

    latex or markdown formatting characters

    oai_token-act-pair · gemini-2.0-flash

    start of sentence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     ExecuteAsync
    -0.74
    BeginContext
    -0.67
     disambiguazione
    -0.65
     parting
    -0.54
     архивлан
    -0.51
     Exacts
    -0.51
    StructEnd
    -0.48
     protoimpl
    -0.48
     الدولى
    -0.48
    يكب
    -0.47
    POSITIVE LOGITS
    ROIT
    0.60
    urably
    0.59
    nitř
    0.57
     تانيه
    0.55
    TargetException
    0.54
    Datuak
    0.52
    vode
    0.51
    extAlignment
    0.49
    monton
    0.49
     vời
    0.48
    Activations Density 5.595%

    No Known Activations