© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13525
    Prev
    Next
    INDEX
    Explanations

    words that start with "bes"

    oai_token-act-pair · gemini-2.0-flash

    the prefix 'Bes'

    np_token-act-pair-logits · gpt-4o-mini
    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
     sn
    -0.43
    徊
    -0.41
     đời
    -0.39
    combine
    -0.38
    ところです
    -0.38
    蚊
    -0.38
    突
    -0.38
     promote
    -0.37
    ause
    -0.36
    ceros
    -0.36
    POSITIVE LOGITS
    SharedDtor
    1.04
     مشين
    0.96
     HasFactory
    0.95
    OGND
    0.86
     ProtoMessage
    0.84
    EndGlobalSection
    0.83
    RTDA
    0.82
    oredCriteria
    0.81
    InputBorder
    0.80
    :✨
    0.77
    Activations Density 0.385%

    No Known Activations