© 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. 4245
    Prev
    Next
    INDEX
    Explanations

    descriptions of a tongue's appearance, including color and texture.

    oai_token-act-pair · gemini-2.0-flash

    technical programming keywords

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

    code snippets

    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
    ModelSerializer
    -0.46
    ClientRect
    -0.44
     relation
    -0.44
    libft
    -0.43
     hlav
    -0.43
     esta
    -0.42
    jface
    -0.42
    dej
    -0.41
     ré
    -0.41
     j
    -0.40
    POSITIVE LOGITS
    matchCondition
    0.89
    ]='\
    0.78
    出版年
    0.76
     Administrativna
    0.65
     ſtate
    0.65
     ModelExpression
    0.64
     chofe
    0.64
     IBOutlet
    0.64
     ftate
    0.64
     ſche
    0.63
    Activations Density 0.655%

    No Known Activations