© 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. 3173
    Prev
    Next
    INDEX
    Explanations

    occurrences of the words "to", "we", "the", and "a", often highlighting phrases with political undertones.

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    NUMX
    -0.67
     Савезне
    -0.66
    Skocz
    -0.66
     CreateTagHelper
    -0.66
    '},
    -0.65
     $("<
    -0.57
    Clik
    -0.56
     there
    -0.56
     photolibrary
    -0.56
    IntoConstraints
    -0.56
    POSITIVE LOGITS
     add
    0.59
     verify
    0.59
     treat
    0.59
     eat
    0.58
     connect
    0.57
     bind
    0.56
     modify
    0.55
     communicate
    0.55
     develop
    0.55
     prove
    0.54
    Activations Density 18.156%

    No Known Activations