© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12891
    Prev
    Next
    INDEX
    Explanations

    the word "do" or "did"

    oai_token-act-pair · gemini-2.0-flash

    say "not"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     not
    -1.50
    not
    -1.09
    Not
    -1.04
     Not
    -1.00
    χι
    -0.90
     bukan
    -0.89
     nicht
    -0.86
     utafitiHapana
    -0.81
     niet
    -0.80
     ikke
    -0.80
    POSITIVE LOGITS
     now
    0.88
    now
    0.82
     NOW
    0.69
    Now
    0.63
     Now
    0.63
    NOW
    0.60
     ahora
    0.59
    Ahora
    0.54
     Ahora
    0.53
    ParseTree
    0.52
    Activations Density 3.190%

    No Known Activations