© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12092
    Prev
    Next
    INDEX
    Explanations

    the word have and other past tense helper verbs.

    oai_token-act-pair · gemini-2.0-flash

    have

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     jspb
    -0.70
     chi̍t
    -0.70
    ImageContext
    -0.70
     متعلقه
    -0.68
    Hochspringen
    -0.66
    astify
    -0.63
     <<<<<<<<<<<<<<
    -0.62
    Asking
    -0.60
    CodeAttribute
    -0.59
    存于互联网档案馆
    -0.59
    POSITIVE LOGITS
    Gdx
    0.45
     bagged
    0.45
     fitted
    0.44
     دیکھیے
    0.44
     bolted
    0.43
    merged
    0.41
    Спорт
    0.40
    وفاته
    0.39
    μί
    0.39
    зулта
    0.39
    Activations Density 5.551%

    No Known Activations