© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14620
    Prev
    Next
    INDEX
    Explanations

    the word "and" or "or," sometimes near words like "decreased" or "even".

    oai_token-act-pair · gemini-2.0-flash

    and/or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     and
    -0.64
    <bos>
    -0.57
     للمعارف
    -0.48
     or
    -0.48
     pos
    -0.47
    th
    -0.45
     Lauf
    -0.44
     E
    -0.44
     '
    -0.44
     الحره
    -0.43
    POSITIVE LOGITS
     myſelf
    0.84
    InSection
    0.82
     becauſe
    0.81
     OMITBAD
    0.81
     ſeveral
    0.77
     typelib
    0.74
     pleaſure
    0.70
     vectorielle
    0.70
     itſelf
    0.69
     themſelves
    0.68
    Activations Density 0.505%

    No Known Activations