© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6941
    Prev
    Next
    INDEX
    Explanations

    various forms of the infinitive 'to' and modal verbs like 'would', 'may', 'can', and 'going to'(future tense)

    oai_token-act-pair · gemini-2.0-flash

    like

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    BufferException
    -0.80
    Бахар
    -0.73
     الرخصة
    -0.67
    KURZBESCHREIBUNG
    -0.64
     незавершена
    -0.63
    HtmlAttribute
    -0.63
    êng
    -0.60
    liothèque
    -0.59
     lenker
    -0.57
     nahilalakip
    -0.57
    POSITIVE LOGITS
     like
    3.36
     Like
    2.52
    Like
    2.48
    like
    2.34
     LIKE
    2.27
     seperti
    1.91
    LIKE
    1.90
     như
    1.63
     مانند
    1.56
     Seperti
    1.54
    Activations Density 3.094%

    No Known Activations