© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7951
    Prev
    Next
    INDEX
    Explanations

    numbers used as adjectives within a broader narrative

    oai_token-act-pair · gemini-2.0-flash

    personal thoughts and experiences

    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
    MemoryWarning
    -0.69
    NOPQRST
    -0.60
     بيها
    -0.59
    CloseOperation
    -0.57
    AxisAlignment
    -0.56
    cyd
    -0.54
     unknownFields
    -0.53
     expérience
    -0.51
     EXPERIENCE
    -0.51
     TextInputType
    -0.49
    POSITIVE LOGITS
     nonUne
    0.64
     protoimpl
    0.58
     conmigo
    0.52
    HtmlAttribute
    0.52
     beant
    0.50
    textTheme
    0.50
    sizeCache
    0.49
     otomatig
    0.48
    Rüyada
    0.47
    Πηγή
    0.46
    Activations Density 12.386%

    No Known Activations