© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8061
    Prev
    Next
    INDEX
    Explanations

    text discussing the autumn/fall season

    oai_token-act-pair · gemini-2.0-flash

    Seasons/Months

    np_max-act-logits · gemini-2.0-flash

    say "seasons/months/holidays" Method used: 2 — tokens after are seasonal/time indicators

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     celebration
    -0.84
     celebrations
    -0.81
     festivals
    -0.80
    +:+
    -0.80
     celebrate
    -0.79
     anniversaries
    -0.79
     fests
    -0.79
     celebrates
    -0.79
    celebr
    -0.79
     celebrating
    -0.77
    POSITIVE LOGITS
     CreateTagHelper
    0.47
    dust
    0.46
    mapStateToProps
    0.44
     postale
    0.44
     dig
    0.44
    uite
    0.42
     Ceramby
    0.41
    BeginContext
    0.41
    ãy
    0.40
    بوابة
    0.40
    Activations Density 2.334%

    No Known Activations