© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14270
    Prev
    Next
    INDEX
    Explanations

    contextual cues related to medical or scientific research studies.

    oai_token-act-pair · gemini-2.0-flash

    Decreasing, going below

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     reduction
    -1.57
     reductions
    -1.55
     Reduction
    -1.54
     lowering
    -1.49
    Reduction
    -1.45
     lowered
    -1.43
     reduced
    -1.43
     lower
    -1.41
     Reduced
    -1.38
     lowers
    -1.38
    POSITIVE LOGITS
    }^{+
    0.40
    щи
    0.38
     превы
    0.37
    marginVertical
    0.36
    fontWeight
    0.36
    marginHorizontal
    0.36
    delà
    0.35
     North
    0.35
    ]>
    0.35
    tellingen
    0.34
    Activations Density 4.206%

    No Known Activations