© 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. 12906
    Prev
    Next
    INDEX
    Explanations

    This neuron appears to be matching on CSS code snippets and potentially some Japanese loan words related to food.

    oai_token-act-pair · gemini-2.0-flash

    no. Method used: 1. Reason: First word in the list

    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
     FV
    -0.61
     vj
    -0.58
     JES
    -0.54
     FZ
    -0.54
    ngrx
    -0.53
    });*/
    -0.52
     zc
    -0.52
    qrstuvwxyz
    -0.52
     CZ
    -0.51
    MigrationBuilder
    -0.51
    POSITIVE LOGITS
    WithMany
    0.52
    akala
    0.50
     múl
    0.50
    alignSelf
    0.49
    itis
    0.49
    ientôt
    0.47
    itik
    0.47
     empêcher
    0.47
     agrícolas
    0.47
    ilik
    0.47
    Activations Density 9.361%

    No Known Activations