© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13078
    Prev
    Next
    INDEX
    Explanations

    words related to abstract concepts or philosophical ideas

    oai_token-act-pair · gemini-2.0-flash

    say "b" 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_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Between
    -0.78
     Between
    -0.77
     OFDb
    -0.70
    Beneath
    -0.70
    sizeCache
    -0.69
     Beneath
    -0.68
    BETWEEN
    -0.67
     interposed
    -0.66
     intervening
    -0.66
    loroethene
    -0.65
    POSITIVE LOGITS
     b
    1.30
     be
    1.14
     bet
    1.09
    be
    1.07
     bef
    0.98
    bet
    0.92
    b
    0.86
    Bet
    0.86
     bel
    0.85
    Be
    0.83
    Activations Density 4.212%

    No Known Activations