© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10035
    Prev
    Next
    INDEX
    Explanations

    punctuation and non-alphanumeric characters

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash

    . Method used: 1 — because MAX_ACTIVATING_TOKENS are identical — "."

    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_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
    -
    -0.60
    bur
    -0.49
    bu
    -0.49
    quad
    -0.44
    po
    -0.44
    bre
    -0.44
    byte
    -0.44
    gen
    -0.44
    ho
    -0.43
    bas
    -0.43
    POSITIVE LOGITS
    latego
    0.83
     marinho
    0.73
    UserScript
    0.67
    wußt
    0.66
    LookAnd
    0.66
     ansatte
    0.66
    colgante
    0.65
     twain
    0.65
    éphane
    0.65
     Cæsar
    0.65
    Activations Density 3.970%

    No Known Activations