© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3773
    Prev
    Next
    INDEX
    Explanations

    descriptions of specific actions and positions, especially those involving violence or strong emotion.

    oai_token-act-pair · gemini-2.0-flash

    Stand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Efq
    -1.11
     Majefty
    -1.09
     ſeveral
    -1.02
     Monfieur
    -1.02
     Diſ
    -0.98
     Anſ
    -0.98
     Reſ
    -0.96
     Chriftian
    -0.95
     tfsi
    -0.91
     Inſ
    -0.91
    POSITIVE LOGITS
    <bos>
    1.13
    ↵
    0.90
    ↵↵
    0.86
    '
    0.68
    1
    0.63
    (
    0.62
    3
    0.60
    5
    0.55
    A
    0.55
    S
    0.54
    Activations Density 0.686%

    No Known Activations