© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7010
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" and opinions being expressed

    oai_token-act-pair · gemini-2.0-flash

    first-person pronouns

    np_token-act-pair-logits · gpt-4o-mini

    first-person pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    ulipas
    -0.44
    BaseAdapter
    -0.43
     doInBackground
    -0.43
    AddTagHelper
    -0.43
    findpost
    -0.42
    uxley
    -0.42
    ніципа
    -0.42
    ArgsConstructor
    -0.42
    esModule
    -0.41
     Lovato
    -0.41
    POSITIVE LOGITS
     me
    3.14
     us
    2.45
     myself
    1.91
     him
    1.89
    me
    1.75
     Me
    1.63
    Me
    1.59
    myself
    1.56
     them
    1.52
     mnie
    1.48
    Activations Density 13.691%

    No Known Activations