© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1864
    Prev
    Next
    INDEX
    Explanations

    strings that contain a quote followed by a plus sign and a digit, often in the context of a parenthesis

    oai_token-act-pair · gemini-2.0-flash

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    SharedDtor
    -0.91
    rungsseite
    -0.83
    Datuak
    -0.80
    /**
    -0.79
     дописавши
    -0.78
    Notae
    -0.77
    rrggbb
    -0.76
     ostavi
    -0.76
    Tembelea
    -0.76
     виправивши
    -0.73
    POSITIVE LOGITS
     “
    0.40
     \
    0.38
     való
    0.33
     bakso
    0.32
     ;
    0.32
     //
    0.31
    zos
    0.30
     chiếu
    0.30
     kaas
    0.30
     m
    0.30
    Activations Density 4.280%

    No Known Activations