© 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. 14951
    Prev
    Next
    INDEX
    Explanations

    terminology around video recording and playback

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "version"

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

    digital media and formats

    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
     виправивши
    -0.73
    AxisAlignment
    -0.73
     priesthood
    -0.69
    WebVitals
    -0.65
     autorytatywna
    -0.63
    StoryboardSegue
    -0.60
    SaveChanges
    -0.60
     EdgeInsets
    -0.59
    jména
    -0.59
     nomads
    -0.58
    POSITIVE LOGITS
    indd
    0.54
     ver
    0.52
     Ver
    0.51
    bes
    0.47
     er
    0.46
     PROTECT
    0.46
    ver
    0.46
     Kop
    0.45
     bes
    0.44
     déta
    0.44
    Activations Density 3.667%

    No Known Activations