© 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. 11890
    Prev
    Next
    INDEX
    Explanations

    the word 'respectively' and nearby text which suggests some statistical study

    oai_token-act-pair · gemini-2.0-flash

    respectively

    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
    TagMode
    -0.76
    respectively
    -0.74
    +#+#
    -0.68
    ̙
    -0.62
     respectively
    -0.62
    ]='\
    -0.62
     AssemblyCulture
    -0.61
    '];?>
    -0.60
    EndContext
    -0.58
    posedge
    -0.58
    POSITIVE LOGITS
     webbplats
    0.51
     anledning
    0.48
    ással
    0.48
     opgenomen
    0.47
    Odkazy
    0.46
     vuoden
    0.45
     triệu
    0.45
    Complete
    0.45
     maroca
    0.44
     pousser
    0.44
    Activations Density 0.782%

    No Known Activations