© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6636
    Prev
    Next
    INDEX
    Explanations

    the preposition "of" and other short prepositions like "for" and "from".

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'of' and related to context

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

    of or for

    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
     to
    -0.68
     the
    -0.67
     that
    -0.65
    ,
    -0.65
     and
    -0.62
     (
    -0.61
     "
    -0.60
     how
    -0.60
     a
    -0.59
     
    -0.58
    POSITIVE LOGITS
     itſelf
    1.20
     BoxDecoration
    1.18
    AnimationsModule
    1.17
     houſe
    1.13
     كومونز
    1.13
    ſelves
    1.12
     MainAxisSize
    1.12
     pleaſure
    1.10
     auffi
    1.09
     purpoſe
    1.09
    Activations Density 1.461%

    No Known Activations