© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12414
    Prev
    Next
    INDEX
    Explanations

    negative press, betrayal, and fighting

    oai_token-act-pair · gemini-2.0-flash

    out

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     للمعارف
    -0.79
     jsPsych
    -0.77
    rungsseite
    -0.69
    RenderAtEndOf
    -0.65
    IntoConstraints
    -0.63
     AssemblyCulture
    -0.61
     صوتيه
    -0.60
    UrlResolution
    -0.60
    WriteTagHelper
    -0.59
     protoimpl
    -0.59
    POSITIVE LOGITS
     out
    3.13
    out
    2.30
     Out
    2.28
    Out
    2.19
     OUT
    2.02
    OUT
    1.73
    outs
    1.55
     outs
    1.38
    アウト
    1.31
    出
    1.30
    Activations Density 4.111%

    No Known Activations