© 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. 8752
    Prev
    Next
    INDEX
    Explanations

    legal or scientific documents/procedures or protocols

    oai_token-act-pair · gemini-2.0-flash

    Code and compilation

    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
     syndicated
    -0.56
     distill
    -0.56
     poll
    -0.56
     multicast
    -0.56
     pamph
    -0.55
     slideshow
    -0.54
     tabular
    -0.54
     reprints
    -0.53
    preprint
    -0.53
     jScrollPane
    -0.52
    POSITIVE LOGITS
     time
    1.02
     age
    1.01
     intensity
    0.99
     strength
    0.99
     length
    0.96
     value
    0.95
     circonstances
    0.94
     reason
    0.93
     condition
    0.91
     ability
    0.89
    Activations Density 12.954%

    No Known Activations