© 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. 13539
    Prev
    Next
    INDEX
    Explanations

    code-like text

    oai_token-act-pair · gemini-2.0-flash

    Code/Configuration files

    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
     الرياضيه
    -0.70
    UnusedPrivate
    -0.69
    :✨
    -0.69
     Monfieur
    -0.64
    featureID
    -0.63
     ainfi
    -0.63
     feroit
    -0.60
    variates
    -0.60
     végétal
    -0.60
     ſmall
    -0.59
    POSITIVE LOGITS
    2
    0.48
    sea
    0.46
    invokeLater
    0.36
    extAlignment
    0.36
    LEncoder
    0.35
    initialize
    0.35
    dehyde
    0.35
    semantics
    0.35
    BeginContext
    0.34
    konferenz
    0.34
    Activations Density 7.633%

    No Known Activations