© 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. 2341
    Prev
    Next
    INDEX
    Explanations

    a mix of sentences with a lot of conjunction, film production, and soldiers

    oai_token-act-pair · gemini-2.0-flash

    future tense

    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
     probably
    -2.28
     perhaps
    -2.22
     maybe
    -2.19
    probably
    -2.09
    Probably
    -2.09
     Probably
    -2.09
     possibly
    -2.05
    perhaps
    -2.05
    maybe
    -2.05
     Perhaps
    -2.03
    POSITIVE LOGITS
    ftagPool
    0.60
    IsContent
    0.57
     defaultstate
    0.50
     TextAppearance
    0.50
    pidou
    0.50
    ].[
    0.49
    ;">
    0.48
    يكب
    0.47
    zzleHttp
    0.47
     Pert
    0.46
    Activations Density 3.962%

    No Known Activations