© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11877
    Prev
    Next
    INDEX
    Explanations

    technical terms related to manufacturing processes and materials science.

    oai_token-act-pair · gemini-2.0-flash

    casting, film

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     الرياضيه
    -1.17
     nakalista
    -1.05
     Monfieur
    -1.04
     poffible
    -1.02
     purpoſe
    -1.02
     ſeveral
    -1.00
     Efq
    -1.00
     Theſe
    -0.98
    tvguidetime
    -0.96
     pleaſure
    -0.95
    POSITIVE LOGITS
     desto
    0.53
     or
    0.48
     dem
    0.46
     O
    0.45
     que
    0.45
     die
    0.45
     Me
    0.44
    sequelize
    0.44
     ce
    0.44
     adalah
    0.42
    Activations Density 2.498%

    No Known Activations