© 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. 11991
    Prev
    Next
    INDEX
    Explanations

    occurrences of the words `the`, `to`, `of`, `can`, `it`, `no`, and `women`, along with related words to form longer phrases.

    oai_token-act-pair · gemini-2.0-flash

    Negative sentiments

    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
    jmniej
    -0.52
    rawdę
    -0.48
    nonatomic
    -0.48
     sẻ
    -0.47
     déput
    -0.46
     sodass
    -0.46
    richTextPanel
    -0.46
     obstante
    -0.44
    adura
    -0.44
    ODO
    -0.44
    POSITIVE LOGITS
     متعلقه
    0.73
     Chwiliwch
    0.65
    adaptiveStyles
    0.65
    BASEPATH
    0.60
    XmlAccessorType
    0.59
    Gön
    0.57
     hObject
    0.57
    RefNanny
    0.56
    multirow
    0.55
    enschappelijke
    0.55
    Activations Density 6.261%

    No Known Activations