© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10062
    Prev
    Next
    INDEX
    Explanations

    filler words and simple comparisons or descriptions

    oai_token-act-pair · gemini-2.0-flash

    adjectives indicating size

    np_token-act-pair-logits · gpt-4o-mini

    big size

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ItemBackground
    -0.49
    SurfaceView
    -0.49
    __*/
    -0.46
     firebaseConfig
    -0.45
    ̸
    -0.42
    سطس
    -0.42
    bleshooting
    -0.42
    charest
    -0.42
    unch
    -0.41
     useAuth
    -0.41
    POSITIVE LOGITS
     large
    2.31
     huge
    2.19
    large
    2.05
    huge
    1.98
     HUGE
    1.92
     massive
    1.86
     enormous
    1.84
     larger
    1.84
    Large
    1.84
     big
    1.81
    Activations Density 2.222%

    No Known Activations