© 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. 14014
    Prev
    Next
    INDEX
    Explanations

    the word "team" and words associated with organizations or groups

    oai_token-act-pair · gemini-2.0-flash

    team

    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
     team
    -1.77
     teams
    -1.66
    team
    -1.59
    Team
    -1.57
     Team
    -1.54
    Teams
    -1.50
     Teams
    -1.45
    teams
    -1.45
     TEAM
    -1.39
    TEAM
    -1.36
    POSITIVE LOGITS
     оригіналу
    0.59
    策
    0.47
     пос
    0.42
    Kons
    0.41
    мат
    0.40
    ঠ
    0.40
    mazione
    0.39
    me
    0.39
     off
    0.39
    せ
    0.39
    Activations Density 1.230%

    No Known Activations