© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7160
    Prev
    Next
    INDEX
    Explanations

    words or phrases expressing a comparative or superlative idea, often in the context of evaluating something.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "still"

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

    still

    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
    ClientSize
    -0.81
    GEBURTSDATUM
    -0.78
    AutoScale
    -0.77
    WithIOException
    -0.74
    #+#
    -0.73
     <=",
    -0.70
    afficheront
    -0.69
    новниш
    -0.67
     appelez
    -0.66
     ErrIntOverflow
    -0.66
    POSITIVE LOGITS
     still
    3.81
    still
    3.42
    Still
    3.31
     Still
    3.30
     STILL
    2.73
    STILL
    2.58
     ancora
    2.41
     ainda
    2.41
     todavía
    2.41
     masih
    2.31
    Activations Density 3.324%

    No Known Activations