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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5803
    Prev
    Next
    INDEX
    Explanations

    code and related terms like properties and deletion

    oai_token-act-pair · gemini-2.0-flash

    Code and multiple languages

    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
    NOPQRST
    -0.71
     defaultstate
    -0.61
    illée
    -0.58
     sogni
    -0.57
    rícula
    -0.55
     Gegenteil
    -0.55
    #+#
    -0.54
     mergeFrom
    -0.54
    GraphicsUnit
    -0.52
    imler
    -0.52
    POSITIVE LOGITS
    Autoritní
    0.65
    :✨
    0.56
    ]};
    0.46
    GetBytes
    0.45
     resourceCulture
    0.45
    ⚭
    0.45
    ubere
    0.44
    SharedDtor
    0.44
     anz
    0.44
    ടെ
    0.42
    Activations Density 1.125%

    No Known Activations