© 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. 11930
    Prev
    Next
    INDEX
    Explanations

    words used in poetry, mixed with words from technical writing

    oai_token-act-pair · gemini-2.0-flash

    common conjunctions and prepositions

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

    common English words

    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
    ratulations
    -1.27
    "):
    
    -1.19
    FTFY
    -1.17
    drawal
    -1.14
    duled
    -1.13
    polation
    -1.12
    æus
    -1.09
    ficulty
    -1.09
    Weiterlesen
    -1.09
    intenance
    -1.08
    POSITIVE LOGITS
    I
    1.08
    that
    1.06
    and
    1.05
    for
    1.01
    it
    0.98
    this
    0.98
    (
    0.97
    in
    0.97
    of
    0.97
    with
    0.96
    Activations Density 0.975%

    No Known Activations