© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9129
    Prev
    Next
    INDEX
    Explanations

    java import statements

    oai_token-act-pair · gemini-2.0-flash

    java

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     java
    -1.46
     Java
    -0.75
    java
    -0.71
    Java
    -0.70
     V
    -0.61
     JAVA
    -0.55
     c
    -0.54
     i
    -0.52
     the
    -0.52
     he
    -0.52
    POSITIVE LOGITS
     SwitchCompat
    0.93
     purpoſe
    0.88
     myſelf
    0.88
     bezeichneter
    0.83
     juſt
    0.83
     Monfieur
    0.83
     Houſe
    0.82
     Chriftian
    0.82
     Efq
    0.82
     raiſ
    0.81
    Activations Density 0.166%

    No Known Activations