© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14656
    Prev
    Next
    INDEX
    Explanations

    words that would be used in police testimony or courtroom proceedings, especially crimes involving theft and firearms.

    oai_token-act-pair · gemini-2.0-flash

    witnessing a crime

    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
     z
    -0.42
     L
    -0.40
     v
    -0.39
     w
    -0.38
    )}{
    -0.38
    HideFlags
    -0.38
     te
    -0.38
    /*!
    -0.36
     meine
    -0.36
     d
    -0.35
    POSITIVE LOGITS
    AddTagHelper
    0.96
     виправивши
    0.95
     Monfieur
    0.89
    ValueStyle
    0.88
     purpoſe
    0.86
     Efq
    0.85
     esternos
    0.85
     Roskov
    0.83
     Wikimedijinoj
    0.83
    Personensuche
    0.82
    Activations Density 15.621%

    No Known Activations