© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1015
    Prev
    Next
    INDEX
    Explanations

    sports teams and players

    oai_token-act-pair · gemini-2.0-flash

    sports teams

    np_max-act · gemini-2.0-flash

    team names

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ս
    -0.47
    RefNanny
    -0.47
    ฯ
    -0.45
    +#+#
    -0.45
    NO
    -0.45
    èlement
    -0.44
    no
    -0.44
    fron
    -0.42
     αυτό
    -0.42
     côtés
    -0.42
    POSITIVE LOGITS
     pinulongan
    0.77
     للاسماء
    0.60
    (!__
    0.60
    følgelig
    0.58
    CodeAttribute
    0.57
     oprot
    0.57
    UALA
    0.57
     kasarigan
    0.56
     Bahkan
    0.56
    DataContract
    0.55
    Activations Density 1.370%

    No Known Activations