© 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. 6594
    Prev
    Next
    INDEX
    Explanations

    the word "earth" and words relating to governance of an area

    oai_token-act-pair · gemini-2.0-flash

    earth

    np_max-act · gemini-2.0-flash

    earth

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     Efq
    -1.23
     myſelf
    -1.19
     itſelf
    -1.12
     Shakspeare
    -1.12
     Houſe
    -1.12
     ſmall
    -1.11
     Jefus
    -1.10
     Theſe
    -1.10
     Anſ
    -1.09
     pleaſure
    -1.09
    POSITIVE LOGITS
    GEBURTSDATUM
    0.75
     so
    0.67
     an
    0.66
    ,
    0.65
    Erreferentziak
    0.65
     as
    0.63
     his
    0.63
     the
    0.59
     he
    0.58
     at
    0.57
    Activations Density 0.582%

    No Known Activations