© 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. 8604
    Prev
    Next
    INDEX
    Explanations

    code with indentation errors

    oai_token-act-pair · gemini-2.0-flash

    Code and paper tape

    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
     الحره
    -0.62
     myſelf
    -0.57
     sacraments
    -0.57
     المعيارى
    -0.54
     Hopf
    -0.54
     Efq
    -0.52
     itſelf
    -0.52
     againſt
    -0.52
     conjectures
    -0.52
     crdi
    -0.51
    POSITIVE LOGITS
     nakalista
    0.79
    GroupLayout
    0.58
    out
    0.57
    array
    0.56
    MigrationBuilder
    0.55
     propOrder
    0.54
    range
    0.54
    IContainer
    0.53
    awtextra
    0.53
    if
    0.53
    Activations Density 1.809%

    No Known Activations