© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4410
    Prev
    Next
    INDEX
    Explanations

    the phrase "cause of action."

    oai_token-act-pair · gemini-2.0-flash

    action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     action
    -3.28
     Action
    -2.86
    action
    -2.81
    Action
    -2.67
     ACTION
    -2.55
     actions
    -2.39
    ACTION
    -2.25
     acción
    -2.25
     Actions
    -2.17
    actions
    -2.11
    POSITIVE LOGITS
    Hauptartikel
    0.50
     TextAppearance
    0.48
     Theile
    0.46
     ciąży
    0.46
    íses
    0.45
    enumi
    0.44
    Slf
    0.43
     ModelExpression
    0.43
    usitis
    0.42
     }}"></
    0.42
    Activations Density 0.535%

    No Known Activations