© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5559
    Prev
    Next
    INDEX
    Explanations

    C++ code, especially class declarations and access modifiers

    oai_token-act-pair · gemini-2.0-flash

    plads

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ”)
    -1.20
    ’)
    -1.13
    )
    -1.10
    )
    -1.08
    ")
    -1.07
    `)
    -1.06
    ')
    -0.97
    __)
    -0.96
    ²)
    -0.95
    /")
    -0.94
    POSITIVE LOGITS
     plads
    0.49
     annuel
    0.48
    </h4>
    0.48
    theless
    0.46
    FieldBuilder
    0.45
    AutoModerator
    0.44
     theſe
    0.43
     myſelf
    0.43
     fédé
    0.42
     originali
    0.42
    Activations Density 0.352%

    No Known Activations