© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10526
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate something is appropriate or correct

    oai_token-act-pair · gemini-2.0-flash

    appropriate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     relevant
    -0.85
     appropriate
    -0.72
     best
    -0.72
     different
    -0.69
     suitable
    -0.63
     typical
    -0.59
     pretty
    -0.57
     most
    -0.57
     either
    -0.56
     pertinent
    -0.56
    POSITIVE LOGITS
     resourceCulture
    1.05
    WebVitals
    1.04
    ंदीखरीदारी
    0.96
    ValueStyle
    0.91
    NameInMap
    0.88
     EnglishChoose
    0.88
     enfans
    0.82
    enskap
    0.81
    tslib
    0.81
     nakalista
    0.80
    Activations Density 1.203%

    No Known Activations