© 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. 1864
    Prev
    Next
    INDEX
    Explanations

    references to locations, directions and transportation in Milwaukee

    oai_token-act-pair · gemini-2.0-flash

    unusual or nonsensical tokens

    np_token-act-pair-logits · gpt-4o-mini

    streets and routes

    np_max-act-logits · gemini-2.0-flash
    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
    /**
    -0.68
     виправивши
    -0.66
    Geplaatst
    -0.65
    /*
    -0.63
     invokingState
    -0.57
    OGND
    -0.57
    Postup
    -0.56
     Guarante
    -0.53
     Zet
    -0.53
     Lied
    -0.52
    POSITIVE LOGITS
    }{*}{
    0.54
     specchio
    0.50
    deepcopy
    0.49
     recevrez
    0.48
     kasarigan
    0.47
    TestBed
    0.46
     mesmas
    0.46
    Rè
    0.45
     blocco
    0.45
     velg
    0.45
    Activations Density 0.259%

    No Known Activations