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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7729
    Prev
    Next
    INDEX
    Explanations

    the word "profile"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     profile
    -2.77
     profiles
    -2.70
     Profile
    -2.59
     Profiles
    -2.50
    Profile
    -2.42
     PROFILE
    -2.38
    profile
    -2.38
     profil
    -2.23
    Profiles
    -2.22
     Profil
    -2.16
    POSITIVE LOGITS
    ruptedException
    0.54
     domenica
    0.47
    HomeAsUpEnabled
    0.46
    initializeApp
    0.45
     ldc
    0.45
    "]();
    0.44
    AccessorTable
    0.44
     heapq
    0.43
     firebaseConfig
    0.42
    lucene
    0.42
    Activations Density 1.259%

    No Known Activations