© 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. 2722
    Prev
    Next
    INDEX
    Explanations

    code snippets with symbols, parenthesis, and brackets, especially those written in C-like and/or scripting languages

    oai_token-act-pair · gemini-2.0-flash

    words with 'ſ' and 'e'

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

    Code

    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
     [
    -1.16
     
    -1.13
     d
    -1.05
     B
    -1.04
     M
    -1.03
     D
    -1.02
     m
    -0.99
     A
    -0.98
     I
    -0.97
     b
    -0.97
    POSITIVE LOGITS
     myſelf
    2.11
     itſelf
    2.09
     pleaſure
    1.96
     Monfieur
    1.92
     Jefus
    1.91
     houſe
    1.88
     Efq
    1.87
     Majefty
    1.85
    ſelf
    1.85
     ſtate
    1.80
    Activations Density 3.229%

    No Known Activations