© 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. 6700
    Prev
    Next
    INDEX
    Explanations

    legal transcripts, or dialogue between parties

    oai_token-act-pair · gemini-2.0-flash

    legal text extracts

    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
     feroit
    -0.77
     argint
    -0.75
    oneofs
    -0.75
     aikaa
    -0.71
     trasparente
    -0.70
     acoper
    -0.66
     készült
    -0.65
     mukana
    -0.64
     pouvoit
    -0.63
     vastaan
    -0.63
    POSITIVE LOGITS
     ft
    0.52
     n
    0.51
    cr
    0.50
     ll
    0.50
    1
    0.50
    -!
    0.50
     \
    0.49
    ft
    0.48
     nd
    0.47
    !\
    0.47
    Activations Density 19.991%

    No Known Activations