© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8222
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "ice" or ways something is filled physically.

    oai_token-act-pair · gemini-2.0-flash

    fill/ice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     d
    -0.61
     fili
    -0.60
    antd
    -0.57
     thirds
    -0.56
     gran
    -0.56
     chic
    -0.54
    ing
    -0.54
     liquid
    -0.54
     fus
    -0.53
    gran
    -0.52
    POSITIVE LOGITS
    IsMutable
    1.12
     étoient
    1.03
     ModelExpression
    1.00
     avoient
    0.99
    AccessorTable
    0.98
    GOTREF
    0.96
    verwijspagina
    0.96
     mergeFrom
    0.96
    (!__
    0.96
     feroit
    0.96
    Activations Density 1.175%

    No Known Activations