© 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. 4265
    Prev
    Next
    INDEX
    Explanations

    code snippets in multiple programming languages

    oai_token-act-pair · gemini-2.0-flash

    code examples and snippets

    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
     take
    -0.82
     create
    -0.81
     find
    -0.78
     consider
    -0.74
     receive
    -0.73
     get
    -0.73
     make
    -0.73
     recover
    -0.73
     adopt
    -0.72
     perform
    -0.71
    POSITIVE LOGITS
    ValueStyle
    0.65
     فريبيس
    0.63
    følgelig
    0.60
    tdessen
    0.56
     actuelles
    0.56
     devriez
    0.56
    IndentedString
    0.56
    oa̍t
    0.55
     avoient
    0.54
     étoient
    0.53
    Activations Density 0.636%

    No Known Activations