© 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. 285
    Prev
    Next
    INDEX
    Explanations

    a mix of hyphenated words, chemical formulas, bible verses, famous people, and the word "the"

    oai_token-act-pair · gemini-2.0-flash

    code, names

    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
     فريبيس
    -0.73
     تضيفلها
    -0.62
    GEBURTSDATUM
    -0.62
    帖最后由
    -0.61
    SourceChecksum
    -0.54
    WriteTagHelper
    -0.53
    المكان
    -0.52
    self
    -0.51
     AspNetCore
    -0.50
    gulama
    -0.50
    POSITIVE LOGITS
     Purch
    0.51
     chi̍t
    0.46
     Clouds
    0.46
    EndInit
    0.46
     Peanuts
    0.45
    vist
    0.45
    marginal
    0.44
    GOTREF
    0.44
    ResumeLayout
    0.44
    πη
    0.43
    Activations Density 2.365%

    No Known Activations