© 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. 15592
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "face" and phrases that contain the word "face."

    oai_token-act-pair · gemini-2.0-flash

    Face-to-face interactions

    np_max-act-logits · 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
     face
    -3.20
     Face
    -3.13
     faces
    -3.11
    Face
    -3.11
    face
    -3.03
     faced
    -2.97
     FACE
    -2.83
     Faces
    -2.78
    faces
    -2.78
    faced
    -2.75
    POSITIVE LOGITS
    rawDesc
    0.73
     Meksiku
    0.53
     Réponses
    0.51
    ciclop
    0.50
    Transkript
    0.49
    tagHelperRunner
    0.47
     jScrollPane
    0.47
     GoogleFonts
    0.46
     通販
    0.46
    Hauptartikel
    0.46
    Activations Density 1.597%

    No Known Activations