© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5246
    Prev
    Next
    INDEX
    Explanations

    mentions of friends or people who are close to each other

    oai_token-act-pair · gemini-2.0-flash

    friend/friends

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     friend
    -2.88
    friend
    -2.33
     Friend
    -2.31
    Friend
    -2.31
     friends
    -2.31
    friends
    -2.02
     FRIEND
    -1.96
     Friends
    -1.94
    Friends
    -1.92
     FRIENDS
    -1.84
    POSITIVE LOGITS
     виправивши
    0.79
    InjectAttribute
    0.74
    SequentialGroup
    0.72
     autorytatywna
    0.71
    keyColumn
    0.59
    tanleria
    0.59
    ULS
    0.58
    rogels
    0.58
    jsxFileName
    0.58
     للمعارف
    0.57
    Activations Density 0.135%

    No Known Activations