© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5893
    Prev
    Next
    INDEX
    Explanations

    the letter "Y" at the beginning of a line or the beginning of the word

    oai_token-act-pair · gemini-2.0-flash

    Y

    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
     كومونز
    -0.54
    égard
    -0.51
    OGND
    -0.49
     Савезне
    -0.47
     naught
    -0.47
    éclairage
    -0.46
     ویکی‌آمباردا
    -0.46
    __":
    
    -0.45
     OFDb
    -0.45
    <bos>
    -0.44
    POSITIVE LOGITS
     Commencez
    0.64
    UGO
    0.61
    PA
    0.61
    VU
    0.60
    Kaynakça
    0.60
    Примітки
    0.59
    jspx
    0.58
    USU
    0.58
    MSA
    0.58
    Hentet
    0.57
    Activations Density 7.177%

    No Known Activations