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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9830
    Prev
    Next
    INDEX
    Explanations

    words related to using or thinking about using a resource

    oai_token-act-pair · gemini-2.0-flash

    use

    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
     sentiers
    -0.38
    6
    -0.37
     cielos
    -0.37
    4
    -0.36
    ++
    -0.36
    制
    -0.35
     pack
    -0.35
     modalités
    -0.35
    Which
    -0.35
    on
    -0.35
    POSITIVE LOGITS
     those
    0.88
     betweenstory
    0.88
    weiterlesen
    0.87
     unknownFields
    0.85
     their
    0.85
    Abraços
    0.84
    __(/*!
    0.84
    IsMutable
    0.82
     MessageBoxIcon
    0.81
    EndInit
    0.80
    Activations Density 12.619%

    No Known Activations