© 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. 14044
    Prev
    Next
    INDEX
    Explanations

    stats about a sports team

    oai_token-act-pair · gemini-2.0-flash

    baseball context

    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
    ContentAsync
    -0.84
    WindowConstants
    -0.71
    NUMX
    -0.64
     AttributeSet
    -0.63
    didSet
    -0.60
    tagHelperRunner
    -0.60
    NameInMap
    -0.60
    },[])
    -0.59
     nahilalakip
    -0.59
    UpInside
    -0.58
    POSITIVE LOGITS
    limus
    0.44
     насељу
    0.44
    ỡng
    0.43
    coders
    0.43
    prefixer
    0.42
    annten
    0.41
     training
    0.41
    ropolitan
    0.40
     betweenstory
    0.40
    Visiting
    0.40
    Activations Density 0.360%

    No Known Activations