© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8290
    Prev
    Next
    INDEX
    Explanations

    a few different patterns, including words that often appear at the beginning of sentences and also phrases related to governments and human nature

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ValueStyle
    -0.59
    /*",
    -0.49
    JsonPropertyName
    -0.45
     undersigned
    -0.42
    =/
    -0.40
    =@
    -0.39
    conceito
    -0.39
    BagLayout
    -0.38
    ślę
    -0.37
    unehmen
    -0.36
    POSITIVE LOGITS
    InteropServices
    0.63
    AndroidJUnit
    0.60
     CreateTagHelper
    0.56
    <bos>
    0.56
    ViewFeatures
    0.56
    ByVersion
    0.54
     jadx
    0.54
    fromnode
    0.54
     محفوظة
    0.53
     '\\;'
    0.53
    Activations Density 1.110%

    No Known Activations