© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11809
    Prev
    Next
    INDEX
    Explanations

    the word "or," "signal" and words related to signaling, and sometimes finds the "if" conjunction

    oai_token-act-pair · gemini-2.0-flash

    Or

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    IntoConstraints
    -0.88
     EconPapers
    -0.77
    &__
    -0.75
     his
    -0.73
     a
    -0.72
     kasarigan
    -0.71
     []:
    -0.70
     rowspan
    -0.69
    ]")]
    -0.68
     تضيفلها
    -0.68
    POSITIVE LOGITS
     itſelf
    1.45
     myſelf
    1.38
     Theſe
    1.38
     raiſ
    1.27
     Houſe
    1.24
     ſche
    1.23
     Reſ
    1.23
     Anſ
    1.22
     poffible
    1.20
     themſelves
    1.18
    Activations Density 2.262%

    No Known Activations