© 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. 11203
    Prev
    Next
    INDEX
    Explanations

    different kinds of code snippets, or code-like syntax

    oai_token-act-pair · gemini-2.0-flash

    }

    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
     MainAxisSize
    -0.89
     propOrder
    -0.85
    principalTable
    -0.81
     فريبيس
    -0.75
     disambiguazione
    -0.72
     &___
    -0.70
     linkovi
    -0.69
    verwijspagina
    -0.69
    AnchorStyles
    -0.69
    richTextPanel
    -0.68
    POSITIVE LOGITS
    picasso
    0.41
     Ocho
    0.41
    ].
    0.40
    STEN
    0.40
     &&
    0.39
    ]
    0.38
    :@"
    0.38
     tác
    0.37
    ه‌
    0.37
    gå
    0.37
    Activations Density 11.964%

    No Known Activations