© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4966
    Prev
    Next
    INDEX
    Explanations

    french language and the letter "l"

    oai_token-act-pair · gemini-2.0-flash

    French text

    np_max-act-logits · gemini-2.0-flash

    apostrophe

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ensement
    -0.74
    LookAnd
    -0.71
    RectangleBorder
    -0.71
    ftagPool
    -0.71
     оригіналу
    -0.71
    RegressionTest
    -0.68
    رشف
    -0.67
    __':
    -0.66
    تقاوى
    -0.65
    rungsseite
    -0.65
    POSITIVE LOGITS
    hébergement
    0.71
    égalité
    0.60
    écriture
    0.58
    enfance
    0.57
    exécution
    0.57
    épaisseur
    0.57
    humidité
    0.56
    égard
    0.55
    écoute
    0.54
    émission
    0.54
    Activations Density 0.626%

    No Known Activations