© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 6545
    Prev
    Next
    INDEX
    Explanations

    words related to heroes and villains in a group

    oai_token-act-pair · gemini-2.0-flash

    Superhero suits descriptions

    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
    K
    -0.46
     K
    -0.42
    FA
    -0.42
     közül
    -0.41
     domingos
    -0.41
     cuidados
    -0.40
    fa
    -0.39
    op
    -0.39
    L
    -0.39
    iale
    -0.38
    POSITIVE LOGITS
    StoryboardSegue
    1.03
    CppCodeGen
    0.89
     AssemblyCompany
    0.87
    jsonwebtoken
    0.83
     Efq
    0.82
     كومونز
    0.82
    WebElementEntity
    0.80
     onix
    0.80
     InputDecoration
    0.78
     himſelf
    0.77
    Activations Density 6.858%

    No Known Activations