© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13619
    Prev
    Next
    INDEX
    Explanations

    code-related concepts as well as concepts involving legal or documented wrongs

    oai_token-act-pair · gemini-2.0-flash

    software licenses

    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
     ve
    -0.51
    ve
    -0.40
     Ve
    -0.36
     typeof
    -0.36
    VE
    -0.35
    ungen
    -0.34
     dali
    -0.33
    hagy
    -0.33
    yntaxException
    -0.33
     vé
    -0.32
    POSITIVE LOGITS
    EndGlobalSection
    1.18
     nakalista
    1.13
     EconPapers
    1.08
     And
    0.98
     và
    0.97
    Portale
    0.92
    UserScript
    0.91
     صوتيه
    0.91
     disambiguazione
    0.89
    esModule
    0.87
    Activations Density 0.147%

    No Known Activations