© 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. 6824
    Prev
    Next
    INDEX
    Explanations

    statistically-oriented information concerning readiness for the future

    oai_token-act-pair · gemini-2.0-flash

    Preparation

    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
     preparation
    -3.23
     prepared
    -3.05
     Preparation
    -2.94
     prepare
    -2.92
    preparation
    -2.84
    prepared
    -2.78
     prepares
    -2.77
     Prepared
    -2.73
     preparing
    -2.69
     prepar
    -2.67
    POSITIVE LOGITS
    kuuta
    0.54
    oyd
    0.52
    rlpool
    0.51
    pyx
    0.50
     насељу
    0.48
    addContainerGap
    0.47
     BitmapFactory
    0.47
    ToBounds
    0.46
    chowa
    0.46
    newtheorem
    0.45
    Activations Density 2.495%

    No Known Activations