© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15824
    Prev
    Next
    INDEX
    Explanations

    the word 'out' or the letters '1', '%', or 'lack' appearing mid sentence

    oai_token-act-pair · gemini-2.0-flash

    say "of"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     of
    -1.85
     của
    -1.79
    ของ
    -1.56
     della
    -1.31
     del
    -1.24
    of
    -1.23
     Of
    -1.23
     des
    -1.21
     της
    -1.19
     ของ
    -1.19
    POSITIVE LOGITS
     Efq
    1.60
     Monfieur
    1.43
     myſelf
    1.41
     Theſe
    1.36
     itſelf
    1.30
     ſeveral
    1.19
     ―――――
    1.19
     Anſ
    1.18
     Jefus
    1.17
     whoſe
    1.17
    Activations Density 1.193%

    No Known Activations