© 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. 13969
    Prev
    Next
    INDEX
    Explanations

    a diverse set of words and phrases that don't seem to have a clear unifying theme, though some are related to location or state, and others are related to negativity or prohibition.

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
     Monfieur
    -1.07
     ſtate
    -1.02
     myſelf
    -1.00
     ſtand
    -1.00
     purpoſe
    -0.97
     faſt
    -0.95
     uſe
    -0.94
     cauſe
    -0.93
     preſent
    -0.91
    SourceChecksum
    -0.90
    POSITIVE LOGITS
     ro
    0.62
     cu
    0.57
     sha
    0.55
     bon
    0.55
     ne
    0.51
     di
    0.49
     pe
    0.48
     la
    0.48
     ho
    0.48
     tra
    0.48
    Activations Density 3.563%

    No Known Activations