© 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. 3381
    Prev
    Next
    INDEX
    Explanations

    rankings of athletic teams and players.

    oai_token-act-pair · gemini-2.0-flash

    terms related to non-English words or specialized terminology

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

    ranking and sports teams

    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
     jLabel
    -0.52
    ValueGenerated
    -0.46
     defaultstate
    -0.46
    PMailer
    -0.45
    Salut
    -0.44
     desain
    -0.44
     banding
    -0.44
     userSchema
    -0.44
     unknownFields
    -0.44
    ])):
    -0.43
    POSITIVE LOGITS
     Schlä
    0.61
    Fonction
    0.60
    Etimología
    0.58
     يتيمه
    0.57
    SourceChecksum
    0.56
    ništ
    0.55
    raeli
    0.50
    IsMutable
    0.50
    führen
    0.49
    toplankton
    0.49
    Activations Density 0.789%

    No Known Activations