© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 235
    Prev
    Next
    INDEX
    Explanations

    the weight or size of a chemical or biological substance

    oai_token-act-pair · gemini-2.0-flash

    weight

    np_max-act · gemini-2.0-flash

    weight

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     weight
    -2.80
    weight
    -2.52
    Weight
    -2.41
     Weight
    -2.30
     WEIGHT
    -2.28
    WEIGHT
    -2.19
     weights
    -2.13
     weigh
    -2.03
    weights
    -1.88
     weighed
    -1.85
    POSITIVE LOGITS
     OMITBAD
    0.70
    posedge
    0.66
    enumi
    0.56
    aja
    0.56
    enumii
    0.55
     Vikipedi
    0.54
    numerusform
    0.54
    specialchars
    0.54
    ediakan
    0.53
    ]();
    0.53
    Activations Density 7.880%

    No Known Activations