© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13358
    Prev
    Next
    INDEX
    Explanations

    NBA-related sports writing

    oai_token-act-pair · gemini-2.0-flash

    NBA basketball

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    esez
    -0.79
    WriteBarrier
    -0.75
    basicConfig
    -0.71
    webElementXpaths
    -0.70
    hamshire
    -0.67
    inSlope
    -0.66
     חיצוניים
    -0.66
     Roskov
    -0.65
     colorWith
    -0.65
    RetentionPolicy
    -0.64
    POSITIVE LOGITS
     DataLoader
    0.54
     oseb
    0.47
     ķ
    0.40
     particuliers
    0.38
     mensuales
    0.37
     lapangan
    0.37
     szív
    0.36
     tangan
    0.36
    ————————————————
    0.35
    praš
    0.35
    Activations Density 1.182%

    No Known Activations