© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11741
    Prev
    Next
    INDEX
    Explanations

    Japanese language posts about programming errors.

    oai_token-act-pair · gemini-2.0-flash

    Japanese sentence endings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     premise
    -0.63
    OGND
    -0.63
     infide
    -0.60
     impossibility
    -0.60
     mision
    -0.58
    endiri
    -0.58
     Marlon
    -0.58
     AIAA
    -0.57
     Lynd
    -0.57
     superiority
    -0.57
    POSITIVE LOGITS
    のですね
    0.78
    んですね
    0.65
    わけです
    0.65
    ところです
    0.64
    わけではない
    0.63
    Datuak
    0.63
    といけない
    0.63
    のですか
    0.59
    んですか
    0.57
    のだろうか
    0.57
    Activations Density 1.050%

    No Known Activations