© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9593
    Prev
    Next
    INDEX
    Explanations

    words that indicate the writer is confident in the statement that they are writing about.

    oai_token-act-pair · gemini-2.0-flash

    advice

    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
    tagHelperRunner
    -0.65
    didSet
    -0.54
     desto
    -0.48
    prnewswire
    -0.47
    IVEREF
    -0.47
     Ott
    -0.47
     Mar
    -0.46
    less
    -0.45
    subpackage
    -0.45
    NgModule
    -0.44
    POSITIVE LOGITS
     ſtate
    0.68
     pleaſure
    0.62
    +#+
    0.62
    醐
    0.60
     purpoſe
    0.60
     ſeveral
    0.59
     auroit
    0.59
    wiſe
    0.58
     greateſt
    0.56
     feroit
    0.55
    Activations Density 9.286%

    No Known Activations