© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5358
    Prev
    Next
    INDEX
    Explanations

    a variety of keywords, including prepositions, pronouns, adjectives, and words related to positive personal qualities.

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     SH
    -0.66
     sur
    -0.65
     Sur
    -0.60
    Lähteet
    -0.59
     Italijani
    -0.56
    SH
    -0.55
    sur
    -0.53
    XtraGrid
    -0.52
     ObjectParameter
    -0.50
     Im
    -0.49
    POSITIVE LOGITS
    Be
    1.05
     Be
    1.02
     BE
    0.97
    be
    0.96
    BE
    0.88
    MLLoader
    0.82
     beg
    0.82
     be
    0.80
    beg
    0.70
     beryllium
    0.70
    Activations Density 5.255%

    No Known Activations