© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6568
    Prev
    Next
    INDEX
    Explanations

    the word "anyway"

    oai_token-act-pair · gemini-2.0-flash

    anyway

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     –
    -0.71
     ‘
    -0.68
     I
    -0.65
     or
    -0.64
    bootstrapcdn
    -0.63
     and
    -0.62
     (
    -0.61
    ↵↵
    -0.60
     "
    -0.57
    POSITIVE LOGITS
     Efq
    1.19
     Theſe
    1.09
     auffi
    1.07
     Monfieur
    1.07
     ſeveral
    1.05
     ainfi
    1.05
     itſelf
    1.05
     myſelf
    1.02
     Jefus
    0.98
     himſelf
    0.94
    Activations Density 1.221%

    No Known Activations