© 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. 6441
    Prev
    Next
    INDEX
    Explanations

    legal jargon specific to statutes and legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    Legal documents

    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
    tagHelperRunner
    -0.66
     Theſe
    -0.65
     becauſe
    -0.61
     CreateTagHelper
    -0.60
     createStore
    -0.59
     GlobalKey
    -0.56
    spesies
    -0.55
     myſelf
    -0.54
    ſelves
    -0.53
     uſ
    -0.53
    POSITIVE LOGITS
     CanadaChoose
    0.54
    тли
    0.51
    jsxFileName
    0.48
     MotionEvent
    0.48
    PullParser
    0.48
    netty
    0.47
     indag
    0.46
     Estate
    0.45
    nable
    0.45
    HasBeenSet
    0.43
    Activations Density 16.659%

    No Known Activations