© 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. 5259
    Prev
    Next
    INDEX
    Explanations

    occurrences of the trigram "nit", plus strings of two or three capital letters followed by lowercase letters, possibly indicating a function or variable name in code

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'vit' or 'nit'

    np_token-act-pair-logits · gpt-4o-mini
    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
     SqlDbType
    -0.81
    alyptus
    -0.76
    WebElementEntity
    -0.74
    ifrance
    -0.71
    úgó
    -0.70
    addPreferredGap
    -0.69
     Efq
    -0.69
     bezeichneter
    -0.69
     &___
    -0.67
     pleaſure
    -0.67
    POSITIVE LOGITS
    sp
    0.49
    vor
    0.44
    ten
    0.43
     chắc
    0.40
     actifs
    0.38
    X
    0.38
     tướng
    0.38
    XT
    0.38
     No
    0.37
    No
    0.37
    Activations Density 0.731%

    No Known Activations