© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1934
    Prev
    Next
    INDEX
    Explanations

    proper nouns or titles followed by a verb

    oai_token-act-pair · gemini-2.0-flash

    references to betrayal and complex relationships

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    xase
    -0.55
    исленность
    -0.53
    TagHelper
    -0.52
    ροσ
    -0.52
    SharedDtor
    -0.51
     oprot
    -0.51
    thâu
    -0.50
    perties
    -0.50
    atrième
    -0.49
     charset
    -0.48
    POSITIVE LOGITS
     noten
    0.50
     Protobuf
    0.50
     onCreateView
    0.48
     \%$\\
    0.48
    unlimited
    0.48
    кла
    0.47
     sy
    0.47
    espół
    0.46
    varing
    0.46
     transfieras
    0.46
    Activations Density 1.018%

    No Known Activations