© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9631
    Prev
    Next
    INDEX
    Explanations

    words that can be interpreted as actions of a person within a narrative

    oai_token-act-pair · gemini-2.0-flash

    entering

    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
     coming
    -1.52
     Coming
    -1.38
    Coming
    -1.30
     COMING
    -1.27
     departing
    -1.25
    coming
    -1.23
     arriving
    -1.18
     graduating
    -1.12
     entering
    -1.11
     passing
    -1.08
    POSITIVE LOGITS
    MethodManager
    0.94
    Hochspringen
    0.88
    uxxxx
    0.75
    ting
    0.73
     оригіналу
    0.72
    +#+#
    0.72
    migrationBuilder
    0.72
    consulté
    0.69
    principalTable
    0.68
     ujednoznacz
    0.68
    Activations Density 2.152%

    No Known Activations