© 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. 10527
    Prev
    Next
    INDEX
    Explanations

    a mixed bag of verbs and adjectives that express positive sentiment or describe general states of being, doing, or seeming.

    oai_token-act-pair · gemini-2.0-flash

    technical or programming terminology

    np_token-act-pair-logits · gpt-4o-mini
    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
    ]--;
    -0.69
    jidad
    -0.60
    évaluateur
    -0.59
    寄り
    -0.56
    Personendaten
    -0.52
    principalColumn
    -0.52
     '<?
    -0.52
    دانشنامهٔ
    -0.50
    HasKey
    -0.50
    ultat
    -0.50
    POSITIVE LOGITS
     Administrativna
    0.63
     AttributeSet
    0.56
    AsUp
    0.54
     utafitiHapana
    0.52
     Roskov
    0.51
     MenuView
    0.49
     Italijanski
    0.48
    ViewGroup
    0.46
     Aws
    0.46
     JpaRepository
    0.45
    Activations Density 0.604%

    No Known Activations