© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12712
    Prev
    Next
    INDEX
    Explanations

    words related to containers and the materials they are made from

    oai_token-act-pair · gemini-2.0-flash

    random objects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    enumii
    -0.73
     CreateTagHelper
    -0.71
    Geplaatst
    -0.68
     useAppContext
    -0.66
    InSection
    -0.66
    archiviato
    -0.65
    ')")
    -0.65
     invokingState
    -0.63
     arşivlendi
    -0.63
     ProtoMessage
    -0.63
    POSITIVE LOGITS
    ConstraintMaker
    0.62
     respirar
    0.43
    SequentialGroup
    0.42
     biologique
    0.41
    Raised
    0.41
     vivos
    0.41
     jsPsych
    0.41
     vs
    0.40
    penup
    0.40
     justiça
    0.39
    Activations Density 1.662%

    No Known Activations