© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10251
    Prev
    Next
    INDEX
    Explanations

    mentions of categories or classifications, specifically concerning military or medical subjects

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    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
    λέον
    -0.74
     Normdatei
    -0.68
     Всё
    -0.63
    minton
    -0.60
    BeginContext
    -0.60
    кож
    -0.60
     Меня
    -0.59
     obstante
    -0.58
    nadequate
    -0.57
     Apalagi
    -0.57
    POSITIVE LOGITS
     démocr
    0.63
     élas
    0.60
     bouteilles
    0.59
     băr
    0.57
     éduc
    0.56
     néer
    0.56
    otra
    0.55
     PROF
    0.55
     présidenti
    0.54
     boî
    0.54
    Activations Density 2.615%

    No Known Activations