© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13576
    Prev
    Next
    INDEX
    Explanations

    periods, possibly those used within code

    oai_token-act-pair · gemini-2.0-flash

    Java code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ContentAsync
    -1.02
    TypedDataSet
    -0.95
    EndGlobalSection
    -0.94
    ✨:
    -0.94
     @"/
    -0.93
    CppMethod
    -0.92
    __":
    -0.88
    __":
    -0.82
    StructEnd
    -0.82
    __':
    -0.82
    POSITIVE LOGITS
     cư
    0.25
     Смо
    0.24
    Pac
    0.24
    script
    0.23
    jwa
    0.23
     pac
    0.22
    лько
    0.22
    ական
    0.21
    no
    0.21
     disso
    0.21
    Activations Density 0.385%

    No Known Activations