© 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. 7030
    Prev
    Next
    INDEX
    Explanations

    strings of words expressing positive opinions about a place or home

    oai_token-act-pair · gemini-2.0-flash

    reviews

    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
    +#+#
    -0.64
     room
    -0.54
     Room
    -0.51
     soutenu
    -0.49
    Room
    -0.48
     kaarangay
    -0.48
    usercontent
    -0.47
     genoux
    -0.47
     rooms
    -0.47
    تقاوى
    -0.47
    POSITIVE LOGITS
    jetunion
    0.61
    ξα
    0.59
     հղումներ
    0.56
    ArrowToggle
    0.55
    DispatchToProps
    0.55
    VERTIS
    0.54
    úrate
    0.54
     TID
    0.54
    ypus
    0.53
    CloseOperation
    0.51
    Activations Density 1.146%

    No Known Activations