© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8663
    Prev
    Next
    INDEX
    Explanations

    the word "arm", often in the context of mechanics or anatomy

    oai_token-act-pair · gemini-2.0-flash

    arm

    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
     arm
    -2.95
     arms
    -2.88
    arm
    -2.59
    arms
    -2.52
     Arm
    -2.48
    Arm
    -2.38
     Arms
    -2.33
    Arms
    -2.13
     ARMS
    -1.86
     brazo
    -1.83
    POSITIVE LOGITS
    EDEFAULT
    0.65
    WebVitals
    0.56
    PageRoute
    0.56
    usermodel
    0.49
    sidemargin
    0.47
    TestBed
    0.47
    nats
    0.47
     województwie
    0.47
    itinéraire
    0.46
    FILED
    0.46
    Activations Density 0.806%

    No Known Activations