© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 4943
    Prev
    Next
    INDEX
    Explanations

    formulas, figures, references, tables and labels, also chemical elements, protein and disease names.

    oai_token-act-pair · gemini-2.0-flash

    words and phrases with 's' and 'f'

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

    -

    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
     A
    -0.86
     I
    -0.84
     y
    -0.84
     B
    -0.84
     O
    -0.83
     H
    -0.82
     E
    -0.80
     l
    -0.79
     e
    -0.79
    ,
    -0.79
    POSITIVE LOGITS
     itſelf
    1.69
     myſelf
    1.38
     Majefty
    1.29
     raiſ
    1.27
    ſelves
    1.26
     uſed
    1.23
     poffible
    1.23
     pleaſure
    1.22
     faſt
    1.21
    ſelf
    1.20
    Activations Density 6.881%

    No Known Activations