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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6186
    Prev
    Next
    INDEX
    Explanations

    the word 'is' and some following words such as articles, prepositions, and one- or two-letter words

    oai_token-act-pair · gemini-2.0-flash

    existential affirmations or statements

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

    is

    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
     Monfieur
    -0.95
     Theſe
    -0.90
     itſelf
    -0.85
     Efq
    -0.84
     myſelf
    -0.82
     themſelves
    -0.81
     pleaſure
    -0.79
     Jefus
    -0.79
     Beſ
    -0.78
     purpoſe
    -0.76
    POSITIVE LOGITS
     difficult
    0.79
     not
    0.78
     a
    0.76
     important
    0.75
     possible
    0.75
     intended
    0.69
     easy
    0.69
     known
    0.68
     available
    0.67
     also
    0.63
    Activations Density 7.483%

    No Known Activations