© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8497
    Prev
    Next
    INDEX
    Explanations

    strings of characters with "tx", "name", "err" or "arri" in them

    oai_token-act-pair · gemini-2.0-flash

    references to specific names or terms

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

    Code/ technical language

    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
     fubject
    -0.58
    
    -0.58
    rinfo
    -0.58
    principalTable
    -0.57
    tagHelperRunner
    -0.54
     UIAlert
    -0.54
    Искәрмәләр
    -0.52
    ]<<"
    -0.51
     Walkover
    -0.51
    styleType
    -0.51
    POSITIVE LOGITS
    NewUrlParser
    0.66
    locken
    0.51
    bakken
    0.49
    存于互联网档案馆
    0.48
    Архівовано
    0.47
    consulté
    0.47
    TestBed
    0.46
    plik
    0.46
    Gweler
    0.46
    Referencie
    0.45
    Activations Density 0.073%

    No Known Activations