© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9564
    Prev
    Next
    INDEX
    Explanations

    the verb "fall" with a medium to high activation

    oai_token-act-pair · gemini-2.0-flash

    words related to downward motion or decline

    np_token-act-pair-logits · gpt-4o-mini

    fall

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    -1.01
    SBATCH
    -1.01
     raiſ
    -0.90
     فريبيس
    -0.85
     pleaſure
    -0.82
     الرياضيه
    -0.82
     Reſ
    -0.79
     iſt
    -0.79
     tranſ
    -0.79
     ſche
    -0.77
    POSITIVE LOGITS
     under
    0.50
     in
    0.50
     http
    0.50
     https
    0.49
    стви
    0.48
     ac
    0.47
     G
    0.46
    ovr
    0.45
    dotenv
    0.43
     to
    0.43
    Activations Density 0.971%

    No Known Activations