© 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. 11753
    Prev
    Next
    INDEX
    Explanations

    phrases like "I can imagine," "hard to imagine," "hard to believe," or "could have."

    oai_token-act-pair · gemini-2.0-flash

    say "guessing" words

    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
     فريبيس
    -0.81
    UnsafeEnabled
    -0.79
     AssemblyCulture
    -0.73
    PreferredItem
    -0.72
    MethodManager
    -0.71
    SequentialGroup
    -0.70
    ABET
    -0.69
     gynhyrchwyd
    -0.68
     Normdatei
    -0.67
     getItemId
    -0.63
    POSITIVE LOGITS
    initializeApp
    0.49
    real
    0.44
     CONC
    0.41
    
    0.41
     kon
    0.40
     cucchiai
    0.39
    Conc
    0.39
     koni
    0.38
    DataSource
    0.38
    مصادر
    0.37
    Activations Density 4.880%

    No Known Activations