© 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. 7922
    Prev
    Next
    INDEX
    Explanations

    the word "acquired" followed sometimes by related terms

    oai_token-act-pair · gemini-2.0-flash

    acquired

    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
    he
    -0.61
    from
    -0.60
    on
    -0.60
    ਘ
    -0.57
    all
    -0.56
    v
    -0.56
    Hansen
    -0.55
    set
    -0.54
     soru
    -0.53
     turístico
    -0.53
    POSITIVE LOGITS
    ſelf
    1.08
     myſelf
    1.08
    ſelves
    1.06
     itſelf
    1.06
     pleaſure
    1.05
     houſe
    0.96
     Reſ
    0.93
     purpoſe
    0.92
     raiſ
    0.91
     themſelves
    0.91
    Activations Density 0.969%

    No Known Activations