© 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. 15012
    Prev
    Next
    INDEX
    Explanations

    numbers followed by time units or the word "for"

    oai_token-act-pair · 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
     betweenstory
    -0.72
     iprot
    -0.72
    ########.
    -0.69
    Personensuche
    -0.65
     mergeFrom
    -0.64
    tagHelperRunner
    -0.63
    Diweddarwch
    -0.57
    ArrowToggle
    -0.57
     oprot
    -0.57
    Rohy
    -0.55
    POSITIVE LOGITS
     Curves
    0.52
    semantics
    0.52
     Muffins
    0.52
    oup
    0.51
     跳转至
    0.49
     HORN
    0.49
    lujah
    0.48
     CAB
    0.47
     Medicines
    0.47
     متعلقه
    0.47
    Activations Density 5.875%

    No Known Activations