© 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. 10989
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "is" and related words like "was" and "are".

    oai_token-act-pair · gemini-2.0-flash

    is

    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
    Known
    -0.59
     Known
    -0.59
    known
    -0.50
     zná
    -0.44
     conocidos
    -0.43
     known
    -0.43
     conocidas
    -0.41
     KNOWN
    -0.41
     conocido
    -0.37
     conocida
    -0.36
    POSITIVE LOGITS
     للاسماء
    0.82
    UnknownFieldSet
    0.76
    entiated
    0.74
    AnimationsModule
    0.73
     BoxDecoration
    0.71
     ExecuteAsync
    0.71
    Nazionale
    0.71
    iastes
    0.71
    تقاوى
    0.70
     kasarigan
    0.69
    Activations Density 3.025%

    No Known Activations