© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3631
    Prev
    Next
    INDEX
    Explanations

    dialogue with greetings

    oai_token-act-pair · gemini-2.0-flash

    specific dialogue and interaction patterns

    np_token-act-pair-logits · gpt-4o-mini

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    جغرافيا
    -0.46
    caso
    -0.46
    țe
    -0.45
    logous
    -0.45
    mení
    -0.44
     preparazione
    -0.44
     [`
    -0.44
     masculina
    -0.44
     Mortimer
    -0.43
    SOUNDBITE
    -0.43
    POSITIVE LOGITS
    PerformLayout
    0.84
    ScopeManager
    0.69
    ⓧ
    0.66
    AsUp
    0.66
     createState
    0.65
    IUrlHelper
    0.64
    曖昧さ回避
    0.60
    éndolo
    0.59
    onViewCreated
    0.57
     which
    0.54
    Activations Density 1.877%

    No Known Activations