© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 743
    Prev
    Next
    INDEX
    Explanations

    conversational language, particularly questions, opinions, exclamations and storytelling.

    oai_token-act-pair · gemini-2.0-flash

    thoughts and opinions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     lèvres
    -0.93
    berdayakan
    -0.88
     myſelf
    -0.87
     RSSSF
    -0.86
     itſelf
    -0.81
     zelve
    -0.81
     larmes
    -0.79
     Monfieur
    -0.79
     prochaines
    -0.78
     ainfi
    -0.78
    POSITIVE LOGITS
     “
    0.55
     m
    0.53
     I
    0.51
     Ver
    0.50
     Z
    0.50
     X
    0.49
     M
    0.49
    TabIndex
    0.49
     é
    0.48
    VELOP
    0.47
    Activations Density 2.677%

    No Known Activations