© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11495
    Prev
    Next
    INDEX
    Explanations

    the word "rest" and words indicating completion or finality

    oai_token-act-pair · gemini-2.0-flash

    rest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     ſever
    -1.48
     itſelf
    -1.45
     ſche
    -1.43
     pleaſure
    -1.42
     houſe
    -1.38
     ſta
    -1.36
     raiſ
    -1.32
     viſ
    -1.32
     ſp
    -1.28
     ſtate
    -1.28
    POSITIVE LOGITS
    ]")]
    1.08
     a
    0.98
    EDEFAULT
    0.94
     the
    0.84
     an
    0.82
     his
    0.79
     kasarigan
    0.77
    rungsseite
    0.76
     all
    0.74
    ponses
    0.74
    Activations Density 1.629%

    No Known Activations