© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11305
    Prev
    Next
    INDEX
    Explanations

    words and punctuation marks indicating sarcasm and rhetorical questions.

    oai_token-act-pair · gemini-2.0-flash

    dont

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     hasn
    -0.88
     hadn
    -0.77
     haven
    -0.75
     Shouldn
    -0.65
     Haven
    -0.63
    Isn
    -0.62
     Couldn
    -0.61
     Isn
    -0.61
    Wasn
    -0.61
     shouldn
    -0.60
    POSITIVE LOGITS
     don
    1.05
     dont
    1.02
    dont
    0.86
    don
    0.86
    Dont
    0.84
    Don
    0.84
     Don
    0.81
     Dont
    0.79
     DONT
    0.75
    DON
    0.73
    Activations Density 2.109%

    No Known Activations