© 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. 10167
    Prev
    Next
    INDEX
    Explanations

    words and short phrases common to scientific papers

    oai_token-act-pair · gemini-2.0-flash

    model

    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
     Enciclopedia
    -0.44
    اد
    -0.44
     COUN
    -0.43
    ioca
    -0.43
    unknownFields
    -0.42
     Masyarakat
    -0.41
     atyp
    -0.40
    Obrázky
    -0.40
    umen
    -0.40
     препратки
    -0.40
    POSITIVE LOGITS
     model
    2.00
     models
    1.84
    model
    1.77
     Model
    1.73
     modelo
    1.68
     MODEL
    1.66
     Models
    1.66
     modelu
    1.60
    Model
    1.58
     모델
    1.56
    Activations Density 2.478%

    No Known Activations