© 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. 11729
    Prev
    Next
    INDEX
    Explanations

    apostrophes

    oai_token-act-pair · gemini-2.0-flash

    quotation marks and similar punctuation

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

    apostrophe

    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
     للاسماء
    -1.00
    featureID
    -0.97
     ISNI
    -0.85
    principalColumn
    -0.85
     referenties
    -0.85
    ьаж
    -0.85
     الحره
    -0.82
     CreateTagHelper
    -0.81
    __':
    -0.79
     Roskov
    -0.79
    POSITIVE LOGITS
    d
    0.58
     s
    0.53
    s
    0.51
     ‘
    0.49
    jau
    0.46
    l
    0.45
    ie
    0.45
    vre
    0.45
    o
    0.44
    ve
    0.43
    Activations Density 1.078%

    No Known Activations