© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1446
    Prev
    Next
    INDEX
    Explanations

    sections of legal documents, especially citations and case references

    oai_token-act-pair · gemini-2.0-flash

    Code, math, or foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     aikaa
    -0.59
    ecore
    -0.57
    ,:);
    -0.57
    znamu
    -0.54
     vastaan
    -0.54
     מים
    -0.54
    prefixes
    -0.53
    AsUp
    -0.53
     tetrachloride
    -0.52
     consecration
    -0.52
    POSITIVE LOGITS
     تضيفلها
    0.67
    ｖ
    0.54
    vle
    0.53
     oy
    0.52
     ‪
    0.52
    सन्दर्भ
    0.52
     jf
    0.51
     isa
    0.50
     wa
    0.50
    <h6>
    0.50
    Activations Density 13.724%

    No Known Activations