© 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. 2388
    Prev
    Next
    INDEX
    Explanations

    language related to legal arguments and cases

    oai_token-act-pair · gemini-2.0-flash

    programming or coding terms

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

    qualifications and uncertainties

    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
    apimachinery
    -0.50
    حياته
    -0.49
     Lage
    -0.49
    vención
    -0.48
    ftagPool
    -0.48
     siglas
    -0.45
     vittoria
    -0.44
    (
    -0.43
     supone
    -0.43
     Syrie
    -0.43
    POSITIVE LOGITS
    tvguidetime
    0.82
    raszam
    0.78
    NUMX
    0.78
    ędziesz
    0.76
     MainAxisSize
    0.75
     kasarigan
    0.70
     snippetHide
    0.67
     CURIAM
    0.60
    Spoljašnje
    0.60
    StoryboardSegue
    0.60
    Activations Density 19.777%

    No Known Activations