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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15495
    Prev
    Next
    INDEX
    Explanations

    personal stories, with a focus on "I" and past tense.

    oai_token-act-pair · gemini-2.0-flash

    life events

    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
    fml
    -0.56
     Move
    -0.55
    Move
    -0.55
    move
    -0.54
     tritium
    -0.51
     nettsted
    -0.50
     literario
    -0.50
    ьаж
    -0.49
     move
    -0.49
     position
    -0.49
    POSITIVE LOGITS
    uxxxx
    0.65
     فريبيس
    0.53
    Hauptartikel
    0.52
    Хьажоргаш
    0.51
    =$?
    0.50
     walked
    0.50
     >=",
    0.50
     CreateTagHelper
    0.49
    ----</
    0.49
    chuk
    0.48
    Activations Density 1.964%

    No Known Activations