© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1297
    Prev
    Next
    INDEX
    Explanations

    horizontal lines using dashes, code snippets, and email footers or headers.

    oai_token-act-pair · gemini-2.0-flash

    dashes and equals

    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
    ."),
    -0.59
     Arjuna
    -0.55
     Esq
    -0.52
     _)
    -0.52
    "}")
    -0.51
    AndEndTag
    -0.48
    .")
    -0.45
     Phnom
    -0.45
     Auro
    -0.45
    opress
    -0.45
    POSITIVE LOGITS
    -------
    0.60
    enumi
    0.59
     doigts
    0.56
     supérieures
    0.56
    ***********/
    0.56
     rayures
    0.56
    ******/
    0.56
     vœux
    0.54
    ********/
    0.54
    URLException
    0.53
    Activations Density 8.108%

    No Known Activations