© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11654
    Prev
    Next
    INDEX
    Explanations

    phrases about sports scores, games, and competitions

    oai_token-act-pair · gemini-2.0-flash

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     مشين
    -0.66
    ChildIndex
    -0.49
    AccessType
    -0.48
    AndEndTag
    -0.47
     accesses
    -0.47
    mentaux
    -0.46
    umbus
    -0.46
     Meksiku
    -0.44
    cienza
    -0.44
     class
    -0.43
    POSITIVE LOGITS
    OrNil
    0.63
     gainera
    0.57
    InjectMocks
    0.56
    onavir
    0.56
     mergeFrom
    0.55
    GOTREF
    0.55
     defaultstate
    0.55
    ConstraintMaker
    0.55
    InteropServices
    0.54
    ificato
    0.53
    Activations Density 0.579%

    No Known Activations