© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5760
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "feed" or related words like "command", "pulse", and "pole" in a technical context

    oai_token-act-pair · gemini-2.0-flash

    feed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    협
    -0.47
    Extension
    -0.45
     extension
    -0.45
    equalTo
    -0.43
     Extension
    -0.42
     EXTENSION
    -0.42
     equalTo
    -0.40
     uğ
    -0.39
     scom
    -0.39
     continuare
    -0.38
    POSITIVE LOGITS
    Personensuche
    0.95
     kasarigan
    0.91
    NameInMap
    0.90
    UpInside
    0.89
     صوتيه
    0.88
    PerformLayout
    0.85
    ScopeManager
    0.81
    __':
    0.78
    SequentialGroup
    0.77
    __":
    0.77
    Activations Density 1.441%

    No Known Activations