© 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. 13652
    Prev
    Next
    INDEX
    Explanations

    parts of code, especially metadata like variable names, types, values, and components of URLs

    oai_token-act-pair · gemini-2.0-flash

    complex data structures or programming terms

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

    code-related structures

    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
    []
    -0.67
    ()
    -0.62
     []
    -0.59
     =
    -0.59
    }
    -0.56
    )
    -0.56
    ;
    -0.55
    !
    -0.54
    =
    -0.52
    ]
    -0.52
    POSITIVE LOGITS
     bezeichneter
    1.02
     Theſe
    0.94
     esternos
    0.94
    躇
    0.93
     Efq
    0.91
    StoryboardSegue
    0.91
    ChildScrollView
    0.88
     الدولى
    0.85
    enderror
    0.84
     '\\;'
    0.84
    Activations Density 5.428%

    No Known Activations