© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14727
    Prev
    Next
    INDEX
    Explanations

    terms and affixes related to scientific discussion

    oai_token-act-pair · gemini-2.0-flash

    adjective suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     whoſe
    -0.69
    ChildScrollView
    -0.60
     myſelf
    -0.59
     stället
    -0.59
     perfons
    -0.57
     themſelves
    -0.57
    曖昧さ回避
    -0.56
     ſeveral
    -0.56
    abstractmethod
    -0.55
    __':
    -0.55
    POSITIVE LOGITS
    tagHelper
    0.57
     виправивши
    0.56
    ļa
    0.53
    ercice
    0.50
    tisseur
    0.49
    zzleHttp
    0.48
     оригіналу
    0.48
    Ӏ
    0.46
    例句
    0.46
     totally
    0.45
    Activations Density 10.872%

    No Known Activations