© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10365
    Prev
    Next
    INDEX
    Explanations

    text that is associated with regulatory bodies, government agencies, or law enforcement

    oai_token-act-pair · gemini-2.0-flash

    Dashes/slashes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     pleaſure
    -1.27
     Efq
    -1.22
     Anſ
    -1.22
     myſelf
    -1.22
     Majefty
    -1.20
     ―――――
    -1.20
     Jefus
    -1.16
     Monfieur
    -1.13
     ſmall
    -1.12
     Diſ
    -1.11
    POSITIVE LOGITS
     v
    0.49
     en
    0.47
     व
    0.42
     e
    0.41
     sal
    0.40
     di
    0.40
     à
    0.39
     la
    0.38
     dé
    0.38
    وى
    0.38
    Activations Density 6.788%

    No Known Activations