© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4207
    Prev
    Next
    INDEX
    Explanations

    words and characters used in scientific or technical writing

    oai_token-act-pair · gemini-2.0-flash

    enrichment

    np_max-act · gemini-2.0-flash

    say "leading space"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     propOrder
    -1.22
    <bos>
    -1.19
     poffe
    -1.02
    AddTagHelper
    -1.01
    хьтан
    -0.98
     nahilalakip
    -0.97
     CreateTagHelper
    -0.96
     ſtate
    -0.91
     raiſ
    -0.90
    AndEndTag
    -0.90
    POSITIVE LOGITS
     as
    0.52
     on
    0.48
     or
    0.43
    <eos>
    0.42
     its
    0.42
     to
    0.42
    FixedSize
    0.41
     don
    0.39
     for
    0.37
    ligente
    0.37
    Activations Density 49.474%

    No Known Activations