© 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. 4889
    Prev
    Next
    INDEX
    Explanations

    mathematical notations, formatting symbols, and separators, likely within a technical document

    oai_token-act-pair · gemini-2.0-flash

    dash

    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
    GEBURTSDATUM
    -0.90
     وتسجيلات
    -0.90
    Референце
    -0.85
    RegressionTest
    -0.80
     Roskov
    -0.75
    stdc
    -0.74
    tanleria
    -0.73
    se
    -0.70
    Παραπομπές
    -0.69
    Hentet
    -0.69
    POSITIVE LOGITS
    the
    0.69
    but
    0.55
    things
    0.54
    bodies
    0.53
    bals
    0.50
    balls
    0.49
    were
    0.49
    bat
    0.48
    bars
    0.47
    bes
    0.47
    Activations Density 12.988%

    No Known Activations