© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8760
    Prev
    Next
    INDEX
    Explanations

    C++ code snippets with variable assignments and get/set operations

    oai_token-act-pair · gemini-2.0-flash

    Brackets and braces

    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
     للمعارف
    -0.88
     vulgaires
    -0.86
     dreamstime
    -0.86
    HostException
    -0.84
    saurus
    -0.81
     Corsa
    -0.81
     Muses
    -0.80
     martyrdom
    -0.77
     coronation
    -0.77
     Jove
    -0.77
    POSITIVE LOGITS
    pro
    0.47
    cri
    0.47
    sk
    0.43
     pro
    0.41
    pu
    0.40
    fl
    0.40
    mo
    0.40
    lan
    0.40
    tra
    0.39
     att
    0.38
    Activations Density 10.616%

    No Known Activations