© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2437
    Prev
    Next
    INDEX
    Explanations

    terms and conditions regarding liability within service agreements or warranties

    oai_token-act-pair · gemini-2.0-flash

    Legal, formal document context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     utafitiHapana
    -0.68
     poveznice
    -0.60
    apimachinery
    -0.52
     participle
    -0.52
    inematics
    -0.52
    odendron
    -0.51
    期刊论文
    -0.51
    EndProject
    -0.51
    brun
    -0.51
    matchCondition
    -0.51
    POSITIVE LOGITS
    ResumeLayout
    0.59
     تانيه
    0.55
     poffible
    0.54
     >=",
    0.52
    eachtet
    0.52
     myſelf
    0.51
     proper
    0.50
     Efq
    0.49
     immédi
    0.49
    Hozzáférés
    0.48
    Activations Density 3.404%

    No Known Activations