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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9164
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of movement with words such as "rotation" "respect" and "movement"

    oai_token-act-pair · gemini-2.0-flash

    respect

    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
     houſe
    -0.93
     ſtate
    -0.90
     purpoſe
    -0.86
     cauſe
    -0.85
     beſt
    -0.84
     itſelf
    -0.82
     AssemblyTitle
    -0.81
     pleaſure
    -0.81
     Houſe
    -0.80
     faſt
    -0.80
    POSITIVE LOGITS
    <bos>
    0.66
    綜合報導
    0.59
    '
    0.50
    ’
    0.42
    WithEmail
    0.42
     StatefulWidget
    0.42
     StatelessWidget
    0.42
     V
    0.42
     hlad
    0.40
    kla
    0.40
    Activations Density 2.330%

    No Known Activations