© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13170
    Prev
    Next
    INDEX
    Explanations

    uses a variety of pronouns, auxiliary verbs, conjunctions, and prepositions while also focusing on legal jargon and terminology

    oai_token-act-pair · gemini-2.0-flash

    Default response.to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Rem
    -0.47
    pare
    -0.47
      
    -0.43
    <?
    -0.43
    Typo
    -0.42
    bibitem
    -0.42
     synap
    -0.41
    Symfony
    -0.40
    Styled
    -0.40
    REME
    -0.40
    POSITIVE LOGITS
     للمعارف
    0.69
    featureID
    0.68
    كويكب
    0.68
    rungsseite
    0.62
    uxxxx
    0.60
     initComponents
    0.60
    μβρίου
    0.59
     StringTokenizer
    0.58
    PreferredItem
    0.57
    ixante
    0.57
    Activations Density 3.751%

    No Known Activations