© 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. 2860
    Prev
    Next
    INDEX
    Explanations

    capitalized first letters and full names

    oai_token-act-pair · gemini-2.0-flash

    words related to self-reference or self-identity

    np_token-act-pair-logits · gpt-4o-mini
    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
    Geplaatst
    -0.45
    webElement
    -0.44
    стер
    -0.44
     ve
    -0.44
     Rag
    -0.43
     ra
    -0.43
     Las
    -0.42
     Ram
    -0.42
     defaultstate
    -0.41
    prepareStatement
    -0.41
    POSITIVE LOGITS
     itſelf
    0.96
     pleaſure
    0.95
     leſs
    0.91
     myſelf
    0.89
     Monfieur
    0.89
     faſt
    0.88
     himſelf
    0.85
     ſeveral
    0.85
     Majefty
    0.84
     theſe
    0.84
    Activations Density 0.315%

    No Known Activations