© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7175
    Prev
    Next
    INDEX
    Explanations

    phrases describing relationships and locations

    oai_token-act-pair · gemini-2.0-flash

    technical terms or phrases

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

    Relationships and cohabitation

    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
    IntoConstraints
    -0.50
    พาะ
    -0.45
    SequentialGroup
    -0.44
    Décès
    -0.43
    łać
    -0.43
     berech
    -0.43
     női
    -0.42
     schmeckt
    -0.41
    ائمة
    -0.41
    Eksteraj
    -0.41
    POSITIVE LOGITS
     ProtoMessage
    0.81
    adaptiveStyles
    0.75
     lenker
    0.73
    تقاوى
    0.67
    parseFrom
    0.67
    دانشنامهٔ
    0.63
     '\\;'
    0.59
    ArgsConstructor
    0.59
    :✨
    0.59
    UnsafeEnabled
    0.58
    Activations Density 0.757%

    No Known Activations