© 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. 10799
    Prev
    Next
    INDEX
    Explanations

    instances of placing blame on the people with the words them, us, debt

    oai_token-act-pair · gemini-2.0-flash

    Putting things in situations

    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
     CreateTagHelper
    -0.86
     snippetHide
    -0.80
     surla
    -0.79
    Vidite
    -0.77
     مشين
    -0.75
    Personensuche
    -0.74
    webElementXpaths
    -0.73
    IVEREF
    -0.72
    Tikang
    -0.70
     réfrig
    -0.69
    POSITIVE LOGITS
     into
    0.48
    to
    0.44
     arran
    0.42
    Agre
    0.42
     towed
    0.40
    ke
    0.39
     ATTENTION
    0.39
     alphabetically
    0.39
     onto
    0.38
    into
    0.38
    Activations Density 10.269%

    No Known Activations