© 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. 13493
    Prev
    Next
    INDEX
    Explanations

    mentions of units of measure (seconds, degrees, minutes) along with its values, mostly in the context of scientific experimentation

    oai_token-act-pair · gemini-2.0-flash

    say "seconds"

    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
    やく
    -0.56
    oulli
    -0.56
    GIVEREF
    -0.55
     Administrativna
    -0.54
     eman
    -0.54
     hissing
    -0.53
    achios
    -0.52
     whistling
    -0.52
    Er
    -0.52
     AHL
    -0.52
    POSITIVE LOGITS
    GEBURTSDATUM
    0.67
    Lähteet
    0.63
    fjspx
    0.62
    oredCriteria
    0.60
     فريبيس
    0.60
    richTextPanel
    0.53
    )‏
    0.52
    Xna
    0.51
    Portail
    0.51
    lectic
    0.50
    Activations Density 3.026%

    No Known Activations