© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11829
    Prev
    Next
    INDEX
    Explanations

    discussions of character death with respect to video games and/or Final Fantasy VII

    oai_token-act-pair · gemini-2.0-flash

    words related to character death and gameplay impact

    np_token-act-pair-logits · gpt-4o-mini

    Final Fantasy context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    ]-->
    -0.62
    GIVEREF
    -0.62
    play
    -0.60
    뀜
    -0.59
    yntaxException
    -0.59
    getShared
    -0.59
    ніципа
    -0.58
    SpringBootTest
    -0.57
     Spiel
    -0.57
     gms
    -0.57
    POSITIVE LOGITS
     незавершена
    0.53
    WriteLiteral
    0.50
     chi̍t
    0.48
     cut
    0.48
    astia
    0.46
     Zwischen
    0.44
    Bakgrunnsstoff
    0.44
    合
    0.44
    oogle
    0.43
     thuyết
    0.42
    Activations Density 1.103%

    No Known Activations