© 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. 5734
    Prev
    Next
    INDEX
    Explanations

    scientific or technical text

    oai_token-act-pair · gemini-2.0-flash

    full

    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
     Sentiment
    -0.81
     Symptom
    -0.81
     Permeability
    -0.80
     peindre
    -0.80
     Fluorescence
    -0.77
     Turbul
    -0.77
     Pigment
    -0.77
     Abstraction
    -0.77
     Inference
    -0.77
     Compression
    -0.77
    POSITIVE LOGITS
    Be
    0.79
    Go
    0.77
    Do
    0.76
    Re
    0.73
    Get
    0.72
    As
    0.72
    First
    0.72
    To
    0.72
    One
    0.72
    Co
    0.71
    Activations Density 44.348%

    No Known Activations