© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5795
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to importance and observations

    oai_token-act-pair · gemini-2.0-flash

    important thing

    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
     EconPapers
    -0.95
     BoxDecoration
    -0.78
    IntoConstraints
    -0.64
     tolu
    -0.63
    #+#
    -0.60
     propOrder
    -0.60
    actylus
    -0.59
     EClass
    -0.58
    +#+#
    -0.58
     SafeMath
    -0.58
    POSITIVE LOGITS
     is
    1.31
     are
    1.10
    ?
    0.62
     seraient
    0.61
     were
    0.61
     then
    0.61
    are
    0.58
    的是
    0.56
     am
    0.54
    ?”
    0.53
    Activations Density 9.963%

    No Known Activations