© 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. 12006
    Prev
    Next
    INDEX
    Explanations

    the word "to" and nearby words.

    oai_token-act-pair · gemini-2.0-flash

    to

    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
     enable
    -0.65
    KommentareTeilen
    -0.64
     enables
    -0.63
    tvguidetime
    -0.62
     onOptions
    -0.61
     Enable
    -0.60
     enabling
    -0.59
     EconPapers
    -0.57
    Enable
    -0.57
    Enabling
    -0.57
    POSITIVE LOGITS
     the
    0.67
    URLException
    0.60
     their
    0.50
    DataSnapshot
    0.49
     your
    0.49
    ->___
    0.48
    ReusableCell
    0.48
    locke
    0.46
     zijne
    0.46
    XmlRootElement
    0.45
    Activations Density 5.787%

    No Known Activations