© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14134
    Prev
    Next
    INDEX
    Explanations

    greetings, closings and conversational filler such as "hey," "hope," "well", and punctuation after these.

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     sandero
    -0.55
     pleaſure
    -0.54
    stdc
    -0.54
     Ejercicio
    -0.54
     nying
    -0.52
     purpoſe
    -0.52
     latine
    -0.52
     impati
    -0.51
     acte
    -0.51
     חיצוניים
    -0.50
    POSITIVE LOGITS
     Do
    0.75
     Don
    0.72
     Say
    0.64
     Make
    0.57
     Be
    0.56
     ProtoMessage
    0.55
     Does
    0.54
     Send
    0.54
    (©
    0.54
    liesslich
    0.53
    Activations Density 4.733%

    No Known Activations