© 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. 12219
    Prev
    Next
    INDEX
    Explanations

    legal jargon from court opinions and statutes

    oai_token-act-pair · gemini-2.0-flash

    1

    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
    expandindo
    -0.56
     سكانية
    -0.56
     the
    -0.56
    цездатний
    -0.52
    jecha
    -0.52
    TestingModule
    -0.52
     an
    -0.50
     autorytatywna
    -0.49
     and
    -0.48
    러나
    -0.47
    POSITIVE LOGITS
    1
    0.77
    0
    0.76
    2
    0.68
    OGND
    0.64
    ọn
    0.60
    AndEndTag
    0.59
    setViewportView
    0.59
    󠁢
    0.57
     Emits
    0.56
    3
    0.56
    Activations Density 41.640%

    No Known Activations