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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 11016
    Prev
    Next
    INDEX
    Explanations

    mentions of legal wrongdoing or investigations involving individuals or groups.

    oai_token-act-pair · gemini-2.0-flash

    Crime and tax evasion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     AssemblyTitle
    -0.60
    PropertyChanging
    -0.56
    scryfall
    -0.54
     defaultstate
    -0.52
     ?>>
    -0.51
    ContentAsync
    -0.46
    toral
    -0.44
     noqa
    -0.44
     nakalista
    -0.44
     ✭✭
    -0.44
    POSITIVE LOGITS
     Chwiliwch
    0.68
    DIPSETTING
    0.58
     transfieras
    0.57
    Rüyada
    0.56
     plane
    0.56
     surla
    0.55
     htmlFor
    0.55
     Plane
    0.54
    RenderAtEndOf
    0.54
     Planes
    0.53
    Activations Density 3.542%

    No Known Activations