© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5065
    Prev
    Next
    INDEX
    Explanations

    words and phrases that suggest the conditional possibility of something happening and attempts to prevent it.

    oai_token-act-pair · gemini-2.0-flash

    avoid causing problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    +#+#
    -0.47
     gern
    -0.47
    an
    -0.44
    μμα
    -0.44
    Њ
    -0.41
    AlterField
    -0.40
    kona
    -0.40
    以外
    -0.40
     GenerationType
    -0.40
    тистика
    -0.39
    POSITIVE LOGITS
     BytesLike
    0.66
     تضيفلها
    0.66
    henswürdigkeiten
    0.65
    SharedDtor
    0.63
     utafitiHapana
    0.63
     droughts
    0.61
     pinulongan
    0.61
    cshtml
    0.61
     robberies
    0.60
    ∬
    0.59
    Activations Density 6.640%

    No Known Activations