© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14272
    Prev
    Next
    INDEX
    Explanations

    text about player signings for sports teams, especially soccer/football

    oai_token-act-pair · gemini-2.0-flash

    technical terminology

    np_token-act-pair-logits · gpt-4o-mini

    Sports teams/player transfers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     egne
    -0.45
     čierna
    -0.43
    tyka
    -0.42
     voile
    -0.42
    xas
    -0.42
    dragen
    -0.42
     hoá
    -0.42
    øver
    -0.42
    Transcription
    -0.41
     createSprite
    -0.40
    POSITIVE LOGITS
    TestingModule
    0.81
    Rhestr
    0.71
    بوابة
    0.68
    ftagPool
    0.67
     GenerationType
    0.65
    UnitTesting
    0.63
     LINEAR
    0.62
    NOPQRST
    0.61
    ocellular
    0.60
    Kanpo
    0.60
    Activations Density 0.579%

    No Known Activations