© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3212
    Prev
    Next
    INDEX
    Explanations

    words related to writing, sports and management

    oai_token-act-pair · gemini-2.0-flash

    describing skills

    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
     goutte
    -0.67
    DockStyle
    -0.64
    findpost
    -0.62
     Paglinawan
    -0.60
     समीक्षक
    -0.57
     gouttes
    -0.57
    seamnă
    -0.57
    basicConfig
    -0.56
    berdayakan
    -0.56
    ècie
    -0.56
    POSITIVE LOGITS
    phemy
    0.54
    itiers
    0.53
    fromnode
    0.51
     sheath
    0.51
    criminator
    0.51
     quiver
    0.51
     objectivity
    0.50
    netics
    0.50
    idavit
    0.50
     prospectus
    0.50
    Activations Density 2.908%

    No Known Activations