© 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. 12994
    Prev
    Next
    INDEX
    Explanations

    a review of a cafe and coffee

    oai_token-act-pair · gemini-2.0-flash

    coffee and tea

    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
     ComVisible
    -0.65
     Barrow
    -0.51
     Վերցված
    -0.50
    ุด
    -0.50
    BindingResult
    -0.49
     Italij
    -0.47
     bianche
    -0.46
     olmaz
    -0.46
    SOUNDBITE
    -0.45
    RenderAtEndOf
    -0.45
    POSITIVE LOGITS
    SharedDtor
    0.68
    tagHelperRunner
    0.66
     GenerationType
    0.64
     HasFactory
    0.60
     >=",
    0.59
    pertory
    0.59
    mybatisplus
    0.58
     WaitForSeconds
    0.56
    AttributeSet
    0.53
     cherchés
    0.53
    Activations Density 0.496%

    No Known Activations