© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3086
    Prev
    Next
    INDEX
    Explanations

    frequently used words

    oai_token-act-pair · gemini-2.0-flash

    subjective impressions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     seems
    -0.98
     Parece
    -0.95
    seems
    -0.95
     parece
    -0.91
     Seems
    -0.86
     seem
    -0.84
     appears
    -0.83
    Looks
    -0.80
    Seems
    -0.80
     Looks
    -0.79
    POSITIVE LOGITS
    PMailer
    0.66
     føl
    0.66
     felt
    0.65
     propOrder
    0.65
    Datuak
    0.65
    RTLI
    0.65
     תה
    0.63
     thought
    0.61
     feared
    0.61
    ）.
    0.60
    Activations Density 2.733%

    No Known Activations