© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13580
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and contractions with high frequency

    oai_token-act-pair · gemini-2.0-flash

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     myſelf
    -1.03
     itſelf
    -1.02
     Efq
    -1.00
     himſelf
    -0.93
     identifies
    -0.93
     holds
    -0.91
     applies
    -0.91
     happens
    -0.90
     goes
    -0.90
     gets
    -0.88
    POSITIVE LOGITS
     am
    0.80
    ’
    0.46
    stdc
    0.45
    '
    0.44
    am
    0.42
     come
    0.40
    yeur
    0.40
     AM
    0.40
    uesia
    0.39
     kasarigan
    0.38
    Activations Density 2.244%

    No Known Activations