© 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. 4103
    Prev
    Next
    INDEX
    Explanations

    a variety of patterns from proper names and math to code and emotional language

    oai_token-act-pair · gemini-2.0-flash

    Hungarian language

    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
    AndEndTag
    -1.01
     InputDecoration
    -0.84
    Autoritní
    -0.76
    ThroughAttribute
    -0.73
     AssemblyCulture
    -0.73
     متعلقه
    -0.71
     the
    -0.71
    AnimationsModule
    -0.69
     distanciation
    -0.66
     ISNI
    -0.65
    POSITIVE LOGITS
     álla
    0.61
     esetben
    0.59
     vizsg
    0.54
     mellett
    0.52
    URN
    0.52
     volna
    0.51
     megfe
    0.51
     felé
    0.50
    solete
    0.49
     szabály
    0.49
    Activations Density 3.297%

    No Known Activations