© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3374
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to hemp, organic products, and personal care.

    oai_token-act-pair · gemini-2.0-flash

    product descriptions/reviews

    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
    κυ
    -0.45
     diag
    -0.44
     الحره
    -0.44
     cuán
    -0.43
    copg
    -0.42
     Lionel
    -0.41
    Diag
    -0.41
    aima
    -0.41
    pektrum
    -0.40
     FIA
    -0.40
    POSITIVE LOGITS
    ThroughAttribute
    0.97
    出版年
    0.71
     Савезне
    0.69
     createState
    0.66
    IsMutable
    0.65
     body
    0.65
    ніципа
    0.64
     disambiguazione
    0.64
     صوتيه
    0.63
     travel
    0.60
    Activations Density 9.641%

    No Known Activations