© 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. 10620
    Prev
    Next
    INDEX
    Explanations

    words ending in "ed", along with some seemingly random words with numbers or letters that could relate to IDs.

    oai_token-act-pair · gemini-2.0-flash

    ed

    np_max-act · gemini-2.0-flash

    ed

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ed
    -1.79
    ever
    -1.36
    ities
    -1.26
    ized
    -1.23
    ised
    -1.19
    ians
    -1.18
    earch
    -1.16
    e
    -1.16
    ian
    -1.15
    ek
    -1.12
    POSITIVE LOGITS
    ISupport
    0.84
    GEBURTSDATUM
    0.83
    ings
    0.78
    est
    0.70
    ere
    0.69
    contentLoaded
    0.68
    ness
    0.65
    twimg
    0.64
    ina
    0.64
    ese
    0.60
    Activations Density 5.523%

    No Known Activations