© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8188
    Prev
    Next
    INDEX
    Explanations

    technical writing that includes units of measure, figures, and references

    oai_token-act-pair · gemini-2.0-flash

    terms related to energy

    np_token-act-pair-logits · gpt-4o-mini

    energy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Wikispecies
    -0.54
     نس
    -0.46
    mirante
    -0.45
     Rücks
    -0.43
     syndic
    -0.43
    muerzo
    -0.43
    getWriter
    -0.42
     BoxFit
    -0.42
     aDecoder
    -0.41
     Moist
    -0.40
    POSITIVE LOGITS
     energy
    0.74
     getItemCount
    0.68
    Energy
    0.67
    Havolalar
    0.65
     Energies
    0.65
     energies
    0.65
     pass
    0.65
     énergie
    0.65
     Energy
    0.64
     صوتيه
    0.64
    Activations Density 3.370%

    No Known Activations