© 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. 12692
    Prev
    Next
    INDEX
    Explanations

    a conjunction of pronouns, auxiliary verbs and "to".

    oai_token-act-pair · 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
     place
    -0.53
    nestjs
    -0.52
     Lijst
    -0.51
    ponses
    -0.49
     aureus
    -0.49
    actos
    -0.49
    блица
    -0.49
     getattr
    -0.49
    сомо
    -0.48
    place
    -0.48
    POSITIVE LOGITS
     happen
    0.85
     Happen
    0.70
    IUrlHelper
    0.69
    出版年
    0.67
    happen
    0.65
     happens
    0.65
    HomeAsUpEnabled
    0.60
     Effect
    0.58
     happened
    0.57
    happens
    0.57
    Activations Density 3.190%

    No Known Activations