© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1579
    Prev
    Next
    INDEX
    Explanations

    Japanese sentences describing a problem and asking for comments

    oai_token-act-pair · gemini-2.0-flash

    coding or technical terminology

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

    Code errors/technical writing

    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
    Negative Logits
    INCREF
    -0.62
    NUMX
    -0.58
    Aiheesta
    -0.50
    leman
    -0.50
    multirow
    -0.48
    brainly
    -0.48
    ""}
    -0.48
    ":"",
    -0.48
     createState
    -0.47
    зво
    -0.47
    POSITIVE LOGITS
    tagHelper
    0.59
    JUDGE
    0.55
     [*]
    0.55
    +#+#
    0.54
     discounting
    0.50
    inalg
    0.50
    RegistryLite
    0.50
     AssemblyVersion
    0.50
     mariée
    0.49
     ProtoMessage
    0.49
    Activations Density 0.545%

    No Known Activations