© 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. 10449
    Prev
    Next
    INDEX
    Explanations

    parts of words, some of which appear to be Scandinavian names or toponyms

    oai_token-act-pair · gemini-2.0-flash

    ase

    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
    Geplaatst
    -0.55
    сторон
    -0.54
    ISTICS
    -0.51
     ABN
    -0.51
    tring
    -0.50
    añ
    -0.50
    oose
    -0.49
     pending
    -0.49
     zipfile
    -0.48
     StringField
    -0.48
    POSITIVE LOGITS
     &___
    0.57
     ویکی‌پدی
    0.53
     jLabel
    0.50
    posedge
    0.50
     <<<<<<<<<<<<<<
    0.50
    出版年
    0.49
    UnitTesting
    0.48
    GeneratedMessage
    0.47
    UserScript
    0.47
    TintMode
    0.47
    Activations Density 0.177%

    No Known Activations