© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12480
    Prev
    Next
    INDEX
    Explanations

    first person pronouns with words implying cognitive activity

    oai_token-act-pair · gemini-2.0-flash

    Losing your mind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    saraba
    -0.78
    enumi
    -0.72
    ſelf
    -0.72
    MessageTagHelper
    -0.68
    ')")
    -0.66
     itſelf
    -0.65
     Efq
    -0.64
    */;
    -0.63
    InstanceState
    -0.63
     Anſ
    -0.62
    POSITIVE LOGITS
     Gegen
    0.51
    どころ
    0.45
     Pro
    0.44
    BuilderFactory
    0.44
    pro
    0.43
    ba
    0.43
     De
    0.42
     who
    0.41
     typically
    0.41
     r
    0.40
    Activations Density 12.815%

    No Known Activations