© 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. 4426
    Prev
    Next
    INDEX
    Explanations

    positive phrases like "a good job" or "a great job"

    oai_token-act-pair · gemini-2.0-flash

    frequent connecting words

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

    a

    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
    RenderAtEndOf
    -1.00
    Cyfeiriadau
    -0.90
     صوتيه
    -0.86
    DoubleQuotes
    -0.86
     تضيفلها
    -0.84
     jsPsych
    -0.81
     disambiguazione
    -0.80
     myſelf
    -0.80
    KommentareTeilen
    -0.79
     simplifié
    -0.79
    POSITIVE LOGITS
     a
    0.49
    くれます
    0.40
     great
    0.39
    Plus
    0.38
     dis
    0.37
     doppio
    0.37
    es
    0.36
    a
    0.36
    default
    0.36
     General
    0.35
    Activations Density 0.441%

    No Known Activations