© 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. 9958
    Prev
    Next
    INDEX
    Explanations

    text discussing potential threats to a country

    oai_token-act-pair · gemini-2.0-flash

    Armed groups

    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
    niosek
    -0.47
    леко
    -0.46
    ukur
    -0.44
    halt
    -0.43
    essions
    -0.43
    Prova
    -0.43
     brug
    -0.42
    field
    -0.42
     Wilson
    -0.42
    /**
    -0.41
    POSITIVE LOGITS
     يتيمه
    0.91
    AddTagHelper
    0.69
    sidemargin
    0.69
     cherchés
    0.68
    الحياه
    0.65
     defStyle
    0.65
    rceil
    0.63
    #+#
    0.61
     WebDriverWait
    0.61
    NOPQRST
    0.60
    Activations Density 9.560%

    No Known Activations