© 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. 84
    Prev
    Next
    INDEX
    Explanations

    words related to companies, particularly their names, founding, or renaming

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    ruptedException
    -0.58
    DebuggerNonUser
    -0.57
     VIVO
    -0.57
     Developing
    -0.54
     developing
    -0.54
    NDC
    -0.54
     numerus
    -0.54
    Developing
    -0.53
    ddots
    -0.53
    posedge
    -0.52
    POSITIVE LOGITS
    клопе
    0.61
    kháu
    0.58
     Picchu
    0.58
    :✨
    0.58
    gridx
    0.54
     onCreateView
    0.52
    twimg
    0.50
    rfloor
    0.50
     مُعرِّف
    0.48
     getRule
    0.48
    Activations Density 9.351%

    No Known Activations