© 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. 8441
    Prev
    Next
    INDEX
    Explanations

    clauses starting with a personal pronoun followed by a modal verb (can, should, would).

    oai_token-act-pair · gemini-2.0-flash

    News article text

    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
     sort
    -0.83
    ########.
    -0.82
    sort
    -0.79
     SORT
    -0.69
     stuff
    -0.68
     sorts
    -0.68
     Sort
    -0.68
    Sort
    -0.63
    SORT
    -0.62
     Gets
    -0.60
    POSITIVE LOGITS
    RefNanny
    0.59
    TagHelper
    0.55
    存于互联网档案馆
    0.51
    日閲覧
    0.51
    MethodImpl
    0.49
     <<<<<<<<<<<<<<
    0.47
     Saltar
    0.45
     invokingState
    0.45
    Demografía
    0.45
     '.')
    0.45
    Activations Density 5.576%

    No Known Activations