© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6622
    Prev
    Next
    INDEX
    Explanations

    sentences containing first-person pronouns, opinions, qualifications and closing remarks

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     Shakspeare
    -1.25
     itſelf
    -1.23
     Theſe
    -1.19
     Jefus
    -1.16
     Houſe
    -1.09
     Monfieur
    -1.06
     myſelf
    -1.05
     Anſ
    -1.04
     Majefty
    -1.03
     Cæsar
    -1.01
    POSITIVE LOGITS
     no
    0.90
     he
    0.88
     we
    0.87
     if
    0.85
     do
    0.85
     it
    0.84
     there
    0.81
     she
    0.81
     in
    0.81
     per
    0.80
    Activations Density 2.706%

    No Known Activations