© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4831
    Prev
    Next
    INDEX
    Explanations

    the phrase "North"

    oai_token-act-pair · gemini-2.0-flash

    North

    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
     שוליים
    -0.68
    expiresIn
    -0.66
     Wikiseite
    -0.64
    Personendaten
    -0.63
    الإنجليزية
    -0.63
    +#+#
    -0.60
    MenuInflater
    -0.58
     ब्रेकडाउन
    -0.58
     الاطلاع
    -0.57
     defire
    -0.56
    POSITIVE LOGITS
     Am
    0.47
    we
    0.46
    wok
    0.45
    wo
    0.44
     تضيفلها
    0.43
    scarlet
    0.42
    Fie
    0.42
    IsMutable
    0.41
    XIX
    0.41
    Am
    0.41
    Activations Density 0.338%

    No Known Activations