© 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. 4294
    Prev
    Next
    INDEX
    Explanations

    the first-person perspective expressing excitement about something and encouraging the reader to check it out

    oai_token-act-pair · gemini-2.0-flash

    cannot/can

    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
     excitement
    -1.23
     excited
    -1.16
     Excited
    -1.11
    Excited
    -1.08
     exciting
    -1.07
     excitedly
    -1.00
    excited
    -0.94
     excites
    -0.93
    Exciting
    -0.85
     eagerly
    -0.83
    POSITIVE LOGITS
     cannot
    0.68
    cannot
    0.66
    Cannot
    0.65
    TypedDataSet
    0.63
     Cannot
    0.62
     can
    0.62
    samt
    0.61
     cant
    0.57
    IndentedString
    0.57
     CANNOT
    0.56
    Activations Density 0.901%

    No Known Activations