© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9411
    Prev
    Next
    INDEX
    Explanations

    the word "public" and its associated context, as well as negation

    oai_token-act-pair · gemini-2.0-flash

    access to information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     public
    -2.89
     Public
    -2.86
    Public
    -2.81
     PUBLIC
    -2.63
    public
    -2.48
    PUBLIC
    -2.36
     publicly
    -2.25
     pública
    -2.16
     öffentliche
    -2.03
     öffentlichen
    -2.02
    POSITIVE LOGITS
    bili
    0.31
    TO
    0.31
     made
    0.30
     Made
    0.30
    на
    0.29
    pp
    0.29
    ana
    0.28
     Armageddon
    0.27
     in
    0.26
    inject
    0.26
    Activations Density 1.412%

    No Known Activations