© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2617
    Prev
    Next
    INDEX
    Explanations

    sections about contacting the author with questions or concerns

    oai_token-act-pair · gemini-2.0-flash

    say questions

    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
    ivably
    -0.58
    stddef
    -0.54
    givings
    -0.54
    SourceChecksum
    -0.54
    Переваги
    -0.54
    instancetype
    -0.53
     بيها
    -0.52
    sizlik
    -0.52
    CppCodeGen
    -0.52
     détour
    -0.52
    POSITIVE LOGITS
    ⓧ
    0.51
     topics
    0.50
    ttää
    0.49
    IntoConstraints
    0.46
     signal
    0.46
    دانشنامهٔ
    0.46
     subjects
    0.45
    Att
    0.45
     Hung
    0.44
     capilar
    0.44
    Activations Density 5.291%

    No Known Activations