© 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. 4902
    Prev
    Next
    INDEX
    Explanations

    text from online dating profiles, potentially female profiles

    oai_token-act-pair · gemini-2.0-flash

    negative contractions

    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
     don
    -1.29
    Don
    -1.16
     didn
    -1.13
     isn
    -1.12
     doesn
    -1.10
    don
    -1.09
    didn
    -1.04
    doesn
    -1.03
     Don
    -1.02
     aren
    -1.02
    POSITIVE LOGITS
    nt
    1.91
     cant
    1.53
     dont
    1.50
     didnt
    1.45
     Ive
    1.43
     doesnt
    1.40
     wasnt
    1.38
     couldnt
    1.38
     Dont
    1.38
     Cant
    1.36
    Activations Density 2.351%

    No Known Activations