© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14612
    Prev
    Next
    INDEX
    Explanations

    dates, times, and relational words to them

    oai_token-act-pair · gemini-2.0-flash

    mentions months and dates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     might
    -0.65
     may
    -0.60
    Carriera
    -0.59
     незавершена
    -0.56
    OrBuilder
    -0.56
    SizeF
    -0.53
    ArgumentParser
    -0.53
    ########.
    -0.52
    :✨
    -0.52
    awaiter
    -0.52
    POSITIVE LOGITS
     Theſe
    0.77
    umą
    0.66
    lijck
    0.66
     fhort
    0.56
     mourut
    0.56
     étoient
    0.55
    vorschaubild
    0.54
     Anſ
    0.53
     Reſ
    0.53
    eſ
    0.52
    Activations Density 1.072%

    No Known Activations