© 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. 8214
    Prev
    Next
    INDEX
    Explanations

    phrases related to surveys or investigative reports

    oai_token-act-pair · gemini-2.0-flash

    terms related to depth and interviews

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

    depth

    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
    RenderAtEndOf
    -0.93
    SourceChecksum
    -0.90
     للمعارف
    -0.89
     betweenstory
    -0.88
    tagHelperRunner
    -0.87
    ########.
    -0.87
    IVEREF
    -0.84
    ArgsConstructor
    -0.82
    rawDesc
    -0.82
    addCriterion
    -0.81
    POSITIVE LOGITS
     in
    1.27
     In
    1.02
     depth
    0.92
    depth
    0.91
    In
    0.83
     indep
    0.82
     IN
    0.78
     deep
    0.78
    Depth
    0.75
    深度
    0.75
    Activations Density 1.001%

    No Known Activations