© 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. 5953
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to professional sports teams, team management, and player performance

    oai_token-act-pair · gemini-2.0-flash

    Sports and employment news

    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
     >=",
    -0.81
    sidemargin
    -0.61
    })));
    -0.61
    extAlignment
    -0.59
    WarningLevel
    -0.59
    Tazama
    -0.58
    Földrajzportál
    -0.55
     ProtoMessage
    -0.54
    potranspiration
    -0.54
    wahati
    -0.53
    POSITIVE LOGITS
     this
    0.60
    jelder
    0.53
     intéress
    0.45
    őle
    0.44
    ctools
    0.44
     labdar
    0.44
    สึก
    0.43
    الثة
    0.43
     Friendly
    0.43
    доб
    0.43
    Activations Density 4.682%

    No Known Activations