© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9524
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating there are two or more options to choose from.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     оригіналу
    -0.64
    httphttps
    -0.53
    Kjelder
    -0.53
     Sloveniji
    -0.52
     devoir
    -0.51
    KommentareTeilen
    -0.51
     menac
    -0.48
     Exactos
    -0.48
    astricht
    -0.47
    efeated
    -0.47
    POSITIVE LOGITS
     unnecessary
    0.58
     overkill
    0.52
    isContained
    0.51
    ])]
    0.49
     inuti
    0.47
    tisseur
    0.47
    ]-->
    0.47
    Rè
    0.46
     nakalista
    0.46
    ISupport
    0.46
    Activations Density 0.468%

    No Known Activations