© 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. 13572
    Prev
    Next
    INDEX
    Explanations

    the word "card" in different contexts, including credit cards, voting cards, and greeting cards

    oai_token-act-pair · gemini-2.0-flash

    card

    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
    KommentareTeilen
    -0.74
    endforeach
    -0.59
    endsection
    -0.58
    kuuta
    -0.55
    konzert
    -0.54
    RestTemplate
    -0.52
     >=",
    -0.52
    ParallelGroup
    -0.52
    athread
    -0.52
     Toussaint
    -0.51
    POSITIVE LOGITS
    GraphicsUnit
    0.57
    #+#
    0.54
     onPostExecute
    0.52
     Egli
    0.51
     Vantage
    0.50
     Reſ
    0.50
     समीक्षक
    0.50
     estimés
    0.49
     defaultstate
    0.49
    ital
    0.49
    Activations Density 2.082%

    No Known Activations