© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10270
    Prev
    Next
    INDEX
    Explanations

    words associated with political proposals or agreements.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     proposed
    -2.91
    proposed
    -2.75
     Proposed
    -2.72
    Proposed
    -2.67
     propose
    -2.61
     proposals
    -2.47
     proposing
    -2.47
     PROPOSED
    -2.42
     proposal
    -2.42
     Proposals
    -2.38
    POSITIVE LOGITS
    izarse
    0.49
    IVer
    0.46
    vierno
    0.45
    estars
    0.45
     klokken
    0.44
     vacanze
    0.43
    ">-
    0.42
     krij
    0.42
     stampa
    0.42
     indoss
    0.42
    Activations Density 2.364%

    No Known Activations