© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13343
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to rotation and direction

    oai_token-act-pair · gemini-2.0-flash

    tokens related to "counter" or "clockwise"

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

    rotation, counter

    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
    rhosis
    -0.65
    dafx
    -0.60
    Cyfeiriadau
    -0.57
     bParam
    -0.56
    transient
    -0.53
     pardoned
    -0.53
     transferencia
    -0.52
     AssemblyProduct
    -0.52
     Exacts
    -0.52
     nudo
    -0.52
    POSITIVE LOGITS
     counter
    1.71
     COUNTER
    1.46
     Counter
    1.45
    counter
    1.42
    Counter
    1.32
    COUNTER
    1.14
     Clock
    1.13
     clockwise
    1.11
     antic
    1.07
     counters
    1.04
    Activations Density 2.751%

    No Known Activations