© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3257
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns, sometimes followed by a verb

    oai_token-act-pair · gemini-2.0-flash

    myself

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ⓧ
    -0.78
     censiti
    -0.77
    Privat
    -0.75
    ymce
    -0.75
     ***!
    -0.72
     Privat
    -0.69
     שוליים
    -0.68
    AutoScaleMode
    -0.67
    ENDO
    -0.66
    -/
    -0.65
    POSITIVE LOGITS
     myſelf
    0.68
    vägen
    0.64
    bbene
    0.63
     maș
    0.62
     anſ
    0.60
     itſelf
    0.60
     Majefty
    0.59
     neceff
    0.59
     iyo
    0.58
     poffible
    0.58
    Activations Density 1.265%

    No Known Activations