© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10252
    Prev
    Next
    INDEX
    Explanations

    clauses that include a verb and adjective

    oai_token-act-pair · gemini-2.0-flash

    just

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    kloped
    -0.69
     <<<<<<<<<<<<<<
    -0.59
    endphp
    -0.57
     مشين
    -0.56
    ]-->
    -0.55
     للاسماء
    -0.54
     gid
    -0.53
    ecore
    -0.53
     Zeit
    -0.52
     BoxFit
    -0.52
    POSITIVE LOGITS
     just
    1.85
    just
    1.79
    Just
    1.48
     JUST
    1.45
     Just
    1.44
     merely
    1.31
    JUST
    1.30
     juste
    1.25
     juſt
    1.20
     simply
    1.12
    Activations Density 3.160%

    No Known Activations