© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11741
    Prev
    Next
    INDEX
    Explanations

    lines containing `#define` or `#include` preprocessor directives in code

    oai_token-act-pair · gemini-2.0-flash

    programming language syntax or definitions

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

    #

    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
    Zeneca
    -0.71
     démocr
    -0.59
    Obrázky
    -0.58
    étaire
    -0.57
     împre
    -0.56
    Демографія
    -0.56
    oa̍t
    -0.56
     rosse
    -0.56
     définiti
    -0.55
    )_/¯
    -0.55
    POSITIVE LOGITS
    StoryboardSegue
    0.93
    principalTable
    0.59
    +#+#
    0.59
    TagHelper
    0.55
    ProcessEvent
    0.53
    ेल
    0.52
     zg
    0.46
    esModule
    0.44
    JsonProperty
    0.44
    Brainz
    0.43
    Activations Density 1.995%

    No Known Activations