© 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. 15249
    Prev
    Next
    INDEX
    Explanations

    Objective-C code, particularly related to UI elements and event handling

    oai_token-act-pair · gemini-2.0-flash

    capitalized words starting with 'A', 'H', 'N', 'I', 'T', or 'S'

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

    code snippets

    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
     itſelf
    -1.48
     myſelf
    -1.45
     raiſ
    -1.41
     Reſ
    -1.38
     pleaſure
    -1.34
     Efq
    -1.32
     Diſ
    -1.32
     Houſe
    -1.31
     ་་
    -1.30
     Monfieur
    -1.29
    POSITIVE LOGITS
     He
    0.90
     I
    0.88
     No
    0.84
     A
    0.83
     T
    0.83
     An
    0.81
     But
    0.80
     H
    0.79
     S
    0.79
     N
    0.79
    Activations Density 3.508%

    No Known Activations