© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11821
    Prev
    Next
    INDEX
    Explanations

    periods and the characters directly preceding them

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    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
    <bos>
    -0.91
    frontmatter
    -0.57
    esercito
    -0.56
    Ắ
    -0.56
     phal
    -0.56
     smtplib
    -0.56
     pymongo
    -0.55
    ViewChild
    -0.55
    Geplaatst
    -0.54
    Superview
    -0.54
    POSITIVE LOGITS
    protoimpl
    0.54
    SPATH
    0.53
     referrerpolicy
    0.51
    exitRule
    0.48
     Nosotros
    0.48
    Шу
    0.47
     henvisninger
    0.47
    Portail
    0.46
     Chwiliwch
    0.45
     الرخصة
    0.44
    Activations Density 0.106%

    No Known Activations