© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6062
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to discounts, acceptance, and limitations pertaining to specific groups or age ranges.

    oai_token-act-pair · gemini-2.0-flash

    identification documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    EDEFAULT
    -0.65
     lenker
    -0.57
     Faso
    -0.54
     Allociné
    -0.52
    Искәрмәләр
    -0.50
     елның
    -0.50
     ddelweddau
    -0.50
     gesprochen
    -0.48
    DIPSETTING
    -0.47
     scanty
    -0.46
    POSITIVE LOGITS
     ID
    0.87
     card
    0.84
    withIdentifier
    0.81
    card
    0.80
    findpost
    0.79
     IDs
    0.78
    Card
    0.77
     Card
    0.76
     cards
    0.72
     id
    0.69
    Activations Density 0.309%

    No Known Activations