© 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. 15710
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to being impressed and feelings

    oai_token-act-pair · gemini-2.0-flash

    expressing sentiment

    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
     consultato
    -0.51
     Spart
    -0.46
    apie
    -0.45
    ourable
    -0.45
     analyse
    -0.43
    Ồ
    -0.43
     analyze
    -0.43
     certaine
    -0.42
    わせる
    -0.42
    ynia
    -0.41
    POSITIVE LOGITS
    stdc
    0.77
     autorytatywna
    0.70
     ويكيميديا
    0.66
     Roskov
    0.66
    PMailer
    0.65
     ModelExpression
    0.65
    Geplaatst
    0.65
    WaitGroup
    0.64
    LabelTagHelper
    0.60
     Suivez
    0.60
    Activations Density 3.381%

    No Known Activations