© 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. 13244
    Prev
    Next
    INDEX
    Explanations

    a discussion about music, specifically Azerbaijani music and instruments

    oai_token-act-pair · gemini-2.0-flash

    folklore and traditions

    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
     صوتيه
    -0.65
    harusnya
    -0.64
    تفصیلات
    -0.61
     fidélité
    -0.56
     détruire
    -0.53
    berdayakan
    -0.53
     Administrativna
    -0.50
     découvertes
    -0.50
    Portail
    -0.49
     journalistes
    -0.49
    POSITIVE LOGITS
    awtextra
    0.82
    +#+#
    0.65
     EconPapers
    0.65
    derry
    0.60
    InvalidProtocol
    0.59
    \{\\
    0.58
    Naissance
    0.54
    CompilerServices
    0.52
     mele
    0.51
    windowFixed
    0.51
    Activations Density 1.268%

    No Known Activations