© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13148
    Prev
    Next
    INDEX
    Explanations

    phrases that contain a word or concept qualified or compared to another with "as".

    oai_token-act-pair · gemini-2.0-flash

    comparisons using "as"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    :+:
    -0.69
    يميديا
    -0.67
     Мексичка
    -0.63
     ddelweddau
    -0.59
     الرياضيه
    -0.58
    Viited
    -0.57
    utilisons
    -0.57
    ⓧ
    -0.56
    batore
    -0.55
    Atsauces
    -0.54
    POSITIVE LOGITS
    XmlAccessType
    0.70
    تقاوى
    0.61
    ViewFeatures
    0.54
    parsedMessage
    0.51
    "?>
    0.50
     GenerationType
    0.49
     Himo
    0.48
     PERSON
    0.47
    esse
    0.47
    بوابة
    0.47
    Activations Density 0.542%

    No Known Activations