© 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. 3026
    Prev
    Next
    INDEX
    Explanations

    words or prefixes starting with "dis"

    oai_token-act-pair · gemini-2.0-flash

    dis

    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
     Rigidbody
    -0.60
    Rigidbody
    -0.51
    ❋
    -0.50
     Arg
    -0.49
    tvguidetime
    -0.49
    ulk
    -0.49
     RemoteException
    -0.48
    rawDesc
    -0.46
    omeness
    -0.46
    Bioaccumulative
    -0.46
    POSITIVE LOGITS
     nakalista
    0.62
    ensement
    0.59
     Diretto
    0.55
     pleaſure
    0.55
     Chriftian
    0.55
     depositphotos
    0.55
     preſent
    0.54
     Monfieur
    0.54
     prefent
    0.54
     stead
    0.54
    Activations Density 0.161%

    No Known Activations