© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11353
    Prev
    Next
    INDEX
    Explanations

    descriptive language, adverbs, simple past tense verbs, and adjectives

    oai_token-act-pair · gemini-2.0-flash

    Setting and nearby objects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    gata
    -0.52
    ffindor
    -0.49
    xically
    -0.48
     besto
    -0.47
    Réponse
    -0.47
     WaitForSeconds
    -0.45
     reng
    -0.45
    商品説明
    -0.45
    isateur
    -0.43
    Downloaded
    -0.43
    POSITIVE LOGITS
     dAtA
    0.63
     InputDecoration
    0.60
    __(/*!
    0.58
    providedIn
    0.57
    MigrationBuilder
    0.54
    PerformLayout
    0.53
     CanadaChoose
    0.52
    XmlAccessType
    0.52
     chré
    0.49
    WarningLevel
    0.49
    Activations Density 2.965%

    No Known Activations