© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3823
    Prev
    Next
    INDEX
    Explanations

    words related to deep understanding or awareness

    oai_token-act-pair · gemini-2.0-flash

    insights and relevant observations

    np_token-act-pair-logits · gpt-4o-mini

    insight

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    NewUrlParser
    -0.82
     Италијани
    -0.81
     GenerationType
    -0.65
    جغرافيا
    -0.63
     viewDidLoad
    -0.62
    into
    -0.61
    Into
    -0.59
     ModelExpression
    -0.59
     Away
    -0.57
    ectoria
    -0.57
    POSITIVE LOGITS
    ContextHolder
    0.47
     to
    0.47
     باخ
    0.47
    }\]
    0.46
    thums
    0.46
     sang
    0.45
    KeySpec
    0.45
    texttt
    0.45
     para
    0.45
    直
    0.45
    Activations Density 1.011%

    No Known Activations