© 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. 11587
    Prev
    Next
    INDEX
    Explanations

    a few seemingly unrelated things: a block of words in a somewhat formal context mentioning "Denmark," words ending in "ons", and a few words related to worship

    oai_token-act-pair · gemini-2.0-flash

    preserved

    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
     sp
    -0.43
     wym
    -0.40
     ber
    -0.39
     som
    -0.38
    ');?>
    -0.38
     the
    -0.38
     AS
    -0.38
    '],$
    -0.37
    )}=\
    -0.37
    賜
    -0.37
    POSITIVE LOGITS
    ^(@
    0.77
    PerformLayout
    0.76
     VIDEOTAPE
    0.75
     iſt
    0.75
    IsMutable
    0.75
    SharedDtor
    0.74
    saraba
    0.74
    脚注の使い方
    0.73
     esternos
    0.72
    Cllr
    0.71
    Activations Density 0.986%

    No Known Activations