© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10105
    Prev
    Next
    INDEX
    Explanations

    mentions of durations of time involving the words "for," "over," or "past," often including the word "years."

    oai_token-act-pair · gemini-2.0-flash

    say "years"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     nearly
    -0.49
     aimer
    -0.44
     मह
    -0.42
    ржа
    -0.41
    Args
    -0.41
    nearly
    -0.41
    願い
    -0.40
    Arguments
    -0.40
     felt
    -0.40
    ニュ
    -0.40
    POSITIVE LOGITS
    Tikang
    0.86
    tagHelperRunner
    0.82
    ChildScrollView
    0.81
    UrlResolution
    0.81
     onPostExecute
    0.79
     AttributeSet
    0.79
    StructEnd
    0.79
    bootstrapcdn
    0.77
     مشين
    0.73
     дописавши
    0.73
    Activations Density 1.516%

    No Known Activations