© 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. 15002
    Prev
    Next
    INDEX
    Explanations

    mentions of durations of time

    oai_token-act-pair · gemini-2.0-flash

    say "years/summers"

    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
     season
    -0.64
    season
    -0.62
     MainAxisSize
    -0.58
    KommentareTeilen
    -0.57
    GraphicsUnit
    -0.53
    &__
    -0.52
    __(/*!
    -0.52
    ConstraintMaker
    -0.52
    imageshack
    -0.51
     Season
    -0.50
    POSITIVE LOGITS
    AndroidJUnit
    0.68
     habet
    0.64
     Insee
    0.63
     quæ
    0.58
     الاطلاع
    0.58
     الحره
    0.57
     rheinland
    0.56
    ształ
    0.55
     ballots
    0.53
    ollectionView
    0.53
    Activations Density 3.566%

    No Known Activations