© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5054
    Prev
    Next
    INDEX
    Explanations

    first-person anecdotes where past events are described with some detail (mentions of names, places, dates, etc.)

    oai_token-act-pair · gemini-2.0-flash

    Actions happening

    np_max-act-logits · gemini-2.0-flash

    say "verbs"

    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
     czemu
    -0.42
     szóci
    -0.42
     cade
    -0.42
     eſ
    -0.41
    évaluateur
    -0.39
     Oboe
    -0.38
    IntoConstraints
    -0.38
    Lara
    -0.37
    一旦
    -0.36
    ؤول
    -0.36
    POSITIVE LOGITS
     walking
    0.82
     strolling
    0.79
    walking
    0.77
     sleeping
    0.76
     asleep
    0.74
     sedang
    0.73
    sitting
    0.73
     sitting
    0.71
    ContentAsync
    0.71
    oredCriteria
    0.71
    Activations Density 0.673%

    No Known Activations