© 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. 12791
    Prev
    Next
    INDEX
    Explanations

    a wide variety of seemingly unrelated code snippets, archaic language, and "clin"

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     
    -0.60
    æus
    -0.57
    ...
    -0.56
    ysmal
    -0.54
    entiel
    -0.54
    ḗ
    -0.53
    tonic
    -0.52
    IONA
    -0.51
     Others
    -0.51
     global
    -0.51
    POSITIVE LOGITS
    <bos>
    1.61
    GEBURTSDATUM
    1.15
     للمعارف
    1.01
     enfans
    0.91
     nakalista
    0.91
    IsContent
    0.88
     fallu
    0.84
    mybatisplus
    0.82
    OGND
    0.82
     aveug
    0.82
    Activations Density 2.040%

    No Known Activations