© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4834
    Prev
    Next
    INDEX
    Explanations

    context related to scheduling a consultation or appointment

    oai_token-act-pair · gemini-2.0-flash

    contacting or making appointments

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

    scheduling and inquiries

    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
     autorytatywna
    -0.81
     ✭✭
    -0.74
     propOrder
    -0.73
     ModelExpression
    -0.69
    MethodManager
    -0.65
     Мексичка
    -0.65
     ISNI
    -0.63
     referenties
    -0.63
    Geplaatst
    -0.63
    #+#
    -0.62
    POSITIVE LOGITS
     won
    0.52
     مفص
    0.45
     Чита
    0.44
    sizlik
    0.42
    yszer
    0.42
    won
    0.42
     ся
    0.42
    oredCriteria
    0.42
     itinéraires
    0.41
     δο
    0.41
    Activations Density 0.446%

    No Known Activations