© 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. 13059
    Prev
    Next
    INDEX
    Explanations

    biographical information about musicians including names, instruments, and roles

    oai_token-act-pair · gemini-2.0-flash

    best or better

    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
    บัติ
    -0.50
    dotta
    -0.44
     gekomen
    -0.42
    RenderAtEndOf
    -0.42
     artikkeli
    -0.41
     gestellt
    -0.40
     pile
    -0.39
    setNome
    -0.39
     شم
    -0.38
    سد
    -0.38
    POSITIVE LOGITS
     best
    2.70
     better
    2.55
    best
    2.42
    better
    2.34
     mejor
    2.25
     meglio
    2.19
     melhor
    2.09
    Best
    2.00
    Better
    1.97
     mieux
    1.96
    Activations Density 1.970%

    No Known Activations