© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14202
    Prev
    Next
    INDEX
    Explanations

    verbs in various tenses with auxiliary verbs like "is", "are", "were."

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'simple'

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

    Positive descriptions

    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
    #
    -1.06
    #-
    -0.65
    #+#
    -0.57
    ##
    -0.55
    \#
    -0.55
    #!
    -0.55
    #
    -0.54
     #
    -0.52
    #/
    -0.51
    #__
    -0.49
    POSITIVE LOGITS
     simply
    0.92
    simply
    0.88
     semplicemente
    0.84
     simplesmente
    0.84
    Хьажоргаш
    0.81
     simplemente
    0.80
    GEBURTSDATUM
    0.79
    ValueStyle
    0.78
    Filmographie
    0.77
     للاسماء
    0.73
    Activations Density 0.939%

    No Known Activations