© 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. 3447
    Prev
    Next
    INDEX
    Explanations

    nouns and teams related to sports

    oai_token-act-pair · gemini-2.0-flash

    Sports

    np_max-act · gemini-2.0-flash
    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
    xffffffff
    -0.48
     erg
    -0.48
    xFFFFFFFF
    -0.46
    DispatchToProps
    -0.46
    sigkeit
    -0.46
     vitae
    -0.46
    UnknownFields
    -0.46
    AccessorTable
    -0.46
    numerusform
    -0.45
    EDES
    -0.45
    POSITIVE LOGITS
    findpost
    0.69
     tartalomajánló
    0.65
     referrerpolicy
    0.65
    __":
    0.63
     дописавши
    0.63
    RTDA
    0.59
    Aholisi
    0.58
     chofe
    0.58
     juſ
    0.56
     HasFactory
    0.56
    Activations Density 2.365%

    No Known Activations