© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11553
    Prev
    Next
    INDEX
    Explanations

    words ending in "al", "ary", "ic", and words relating to phone numbers and errors in other languages

    oai_token-act-pair · gemini-2.0-flash

    ske

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     méri
    -0.72
     تضيفلها
    -0.70
     مرئيه
    -0.68
     récomp
    -0.68
    MathML
    -0.65
    AutoScaleMode
    -0.64
     délic
    -0.63
    orteur
    -0.63
     ainfi
    -0.63
     TAMBÉM
    -0.63
    POSITIVE LOGITS
    typal
    0.56
    lamic
    0.54
     combat
    0.54
    IONAL
    0.52
     lesser
    0.52
     de
    0.51
    GRAPHICAL
    0.51
    atic
    0.51
     re
    0.50
    tual
    0.50
    Activations Density 0.513%

    No Known Activations