© 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. 94
    Prev
    Next
    INDEX
    Explanations

    code related to data formatting

    oai_token-act-pair · gemini-2.0-flash

    Code and data structures

    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
    -1.06
     myſelf
    -0.92
     purpoſe
    -0.82
     Cæsar
    -0.82
     itſelf
    -0.81
     iſt
    -0.81
     Anfitrión
    -0.80
     uſed
    -0.79
     againſt
    -0.79
     cauſe
    -0.79
    POSITIVE LOGITS
     
    0.41
    .
    0.39
    achal
    0.31
     fa
    0.30
    ,
    0.27
    ,<
    0.26
     ri
    0.26
    ra
    0.26
    <eos>
    0.25
     li
    0.25
    Activations Density 5.413%

    No Known Activations