© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12851
    Prev
    Next
    INDEX
    Explanations

    words prefixed with "un-", "non-", or implying some negation.

    oai_token-act-pair · gemini-2.0-flash

    scientific and legal contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ConstraintMaker
    -0.55
     فريبيس
    -0.51
    ⓧ
    -0.47
    expandindo
    -0.47
    afficheront
    -0.46
     næste
    -0.44
    derdag
    -0.44
     Италијани
    -0.43
    }))
    -0.42
    xins
    -0.42
    POSITIVE LOGITS
    BASEPATH
    0.56
    DIPSETTING
    0.53
    ImageField
    0.52
    partimento
    0.50
    DateTimeField
    0.49
    ImageContext
    0.49
    zheimer
    0.49
    ElementType
    0.49
     hơn
    0.48
    cader
    0.48
    Activations Density 1.836%

    No Known Activations