© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3085
    Prev
    Next
    INDEX
    Explanations

    string names that are declared as private in Java code related to serialized data

    oai_token-act-pair · gemini-2.0-flash

    say "String"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Personensuche
    -1.25
    MigrationBuilder
    -1.23
    GEBURTSDATUM
    -1.20
     utafitiHapana
    -1.18
     CreateTagHelper
    -1.16
    tonode
    -1.11
    SBATCH
    -1.11
    Rhestr
    -1.09
    matchCondition
    -1.05
    CppMethod
    -1.04
    POSITIVE LOGITS
     
    0.47
     st
    0.45
     O
    0.42
     Sp
    0.38
     sp
    0.38
    ş
    0.36
    Sp
    0.36
    stre
    0.36
    ar
    0.35
    <eos>
    0.35
    Activations Density 6.154%

    No Known Activations