© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3671
    Prev
    Next
    INDEX
    Explanations

    superlatives and competitive titles for sports or politics

    oai_token-act-pair · gemini-2.0-flash

    sports statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    MLLoader
    -0.88
    GOTREF
    -0.84
    principalColumn
    -0.82
    ftagPool
    -0.82
    LookAnd
    -0.79
    elemField
    -0.78
    UnusedPrivate
    -0.77
    InitVars
    -0.75
    +#+
    -0.73
    IsContent
    -0.73
    POSITIVE LOGITS
     professional
    0.43
    irus
    0.43
     almost
    0.42
    ülü
    0.41
     ter
    0.41
    торы
    0.40
     naj
    0.40
    ukov
    0.40
    Sze
    0.40
     major
    0.40
    Activations Density 2.969%

    No Known Activations