© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4406
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly related to media observables

    oai_token-act-pair · gemini-2.0-flash

    code syntax or technical terms

    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
     IBOutlet
    -0.82
    ")));
    -0.74
     lyre
    -0.72
    ]));
    -0.70
     doubtnut
    -0.69
     photolibrary
    -0.69
    tagHelperRunner
    -0.68
    expandindo
    -0.68
     itſelf
    -0.66
     yourselves
    -0.66
    POSITIVE LOGITS
    uc
    0.51
    市镇
    0.48
     Mc
    0.47
    p
    0.46
    Schedulers
    0.46
    Mc
    0.44
     segü
    0.44
     contacter
    0.43
    //
    0.42
     next
    0.42
    Activations Density 1.442%

    No Known Activations