© 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. 12984
    Prev
    Next
    INDEX
    Explanations

    the most common word, "the", and dialogue between people

    oai_token-act-pair · gemini-2.0-flash

    concepts related to hearing

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

    hearing

    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
     Chwiliwch
    -0.51
     eye
    -0.50
     Blick
    -0.50
     Inspect
    -0.48
    eye
    -0.47
     Eye
    -0.46
     eyes
    -0.46
     viewing
    -0.45
    Inspect
    -0.43
     inspect
    -0.43
    POSITIVE LOGITS
     listening
    2.25
     listen
    2.20
     ears
    2.19
     listened
    2.16
     listeners
    2.14
     listener
    2.11
     hearing
    2.09
     heard
    2.08
     Listen
    2.06
     listens
    2.06
    Activations Density 4.711%

    No Known Activations